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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events happening in a social context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of serious health concerns or risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.56
     Whitman
    -0.56
     looph
    -0.50
    ropolitan
    -0.49
     renamed
    -0.48
     NAACP
    -0.47
     PKK
    -0.47
     "'
    -0.47
     Surprise
    -0.47
    guyen
    -0.47
    POSITIVE LOGITS
     ;)
    0.73
    !.
    0.73
    .</
    0.72
    !".
    0.69
     ðŁĻĤ
    0.69
     :)
    0.66
     haha
    0.66
    $.
    0.66
    %.
    0.66
    .�
    0.64
    Act Density 1.585%

    No Known Activations