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

    Neuronpedia

    INDEX
    Explanations

    statements and assertions about official actions or derived statements

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

    Text following reporting verbs

    np_acts-logits-general · gemini-2.0-flash

    reporting "its" claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.78
     myself
    -0.70
     purpoſe
    -0.67
     yourself
    -0.67
    öglichkeiten
    -0.59
     himſelf
    -0.59
    はじめに
    -0.57
     personlig
    -0.56
    িনি
    -0.55
    cesis
    -0.55
    POSITIVE LOGITS
     its
    1.86
     itself
    1.55
     Its
    1.43
    Its
    1.39
     Itself
    1.33
    itself
    1.23
    its
    1.20
    在其
    1.05
    它的
    0.99
     ITS
    0.86
    Act Density 0.934%

    No Known Activations