Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to accountability and public scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opinions, thoughts, or feelings expressed publicly

    np_acts-logits-general · gemini-2.0-flash

    publicly expressing thoughts or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.58
    LikeLiked
    -0.52
     للاسماء
    -0.50
     nakalista
    -0.49
     TextAppearance
    -0.47
     göre
    -0.46
    LookAnd
    -0.45
    UnknownFieldSet
    -0.45
    MigrationBuilder
    -0.44
     Ayres
    -0.44
    POSITIVE LOGITS
     publicly
    1.93
     aloud
    1.33
     openly
    1.29
     öffentlich
    1.26
     pública
    1.24
     verbally
    1.23
     orally
    1.17
     public
    1.17
     loudly
    1.12
     kepada
    1.08
    Act Density 0.392%

    No Known Activations