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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and community concerns, including references to political, environmental, and social topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words that signify significant actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.86
    usterity
    -0.83
    enta
    -0.81
    elta
    -0.76
    aepernick
    -0.75
    onica
    -0.74
    ighed
    -0.72
    ĻĤ
    -0.71
    Wire
    -0.70
    apest
    -0.69
    POSITIVE LOGITS
     expects
    0.74
     somew
    0.74
     vice
    0.73
     invests
    0.71
     intends
    0.66
     acknowledges
    0.63
     whether
    0.63
     accepts
    0.63
     congratulate
    0.62
     guessed
    0.62
    Act Density 0.172%

    No Known Activations