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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by present continuous verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal states or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.76
    Scroll
    -0.67
    ancy
    -0.64
    olor
    -0.62
    pedia
    -0.62
    prints
    -0.62
     Rescue
    -0.60
    ede
    -0.59
     Liberties
    -0.59
    enthal
    -0.58
    POSITIVE LOGITS
     confronted
    1.08
     asked
    0.96
     faced
    0.96
     tempted
    0.93
     done
    0.91
     challenged
    0.88
     attacked
    0.88
     interacting
    0.86
     surrounded
    0.86
     approached
    0.86
    Act Density 0.122%

    No Known Activations