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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and references to personal experiences

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

    Preceding tokens are personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    enjoy their, regarding same, I wrote, your work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.48
    pective
    -0.46
     réfrig
    -0.42
    MigrationBuilder
    -0.42
    pushFollow
    -0.41
     dams
    -0.41
     various
    -0.41
    popd
    -0.41
     accompanying
    -0.40
    sizePolicy
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.57
    jsii
    0.53
    
    0.52
     nakalista
    0.51
     nahilalakip
    0.47
     snippetHide
    0.47
     this
    0.45
     تضيفلها
    0.43
    ConstraintMaker
    0.43
    Tikang
    0.43
    Act Density 0.250%

    No Known Activations