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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urations
    -0.86
    Pad
    -0.75
    word
    -0.71
    rav
    -0.67
    iverse
    -0.64
    ruction
    -0.63
    imon
    -0.62
    etsk
    -0.62
    DEN
    -0.62
     Verb
    -0.61
    POSITIVE LOGITS
    wide
    0.88
    eers
    0.81
    ically
    0.75
    eering
    0.75
    liness
    0.74
    fare
    0.73
    folk
    0.72
    geist
    0.72
     evolves
    0.70
     indo
    0.68
    Act Density 0.020%

    No Known Activations