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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical actions and situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of severe legal actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.66
    ":{"
    -0.60
    VERTISEMENT
    -0.56
    advertising
    -0.56
    æ©Ł
    -0.56
    âĢ
    -0.54
    >]
    -0.54
    ":[{"
    -0.53
    Auth
    -0.53
    )}
    -0.52
    POSITIVE LOGITS
     everywhere
    0.89
     but
    0.80
     though
    0.80
     till
    0.75
     however
    0.73
     meanwhile
    0.73
     again
    0.71
     now
    0.67
     and
    0.67
     here
    0.67
    Act Density 1.053%

    No Known Activations