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

    Neuronpedia

    INDEX
    Explanations

    mentions of public entities, government-related opinions, and statistical information

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political issues affecting the public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cooldown
    -0.60
    ++;
    -0.59
     };
    -0.58
     typed
    -0.54
     tweeted
    -0.53
    cffff
    -0.52
     trough
    -0.51
     Accessed
    -0.51
     sclerosis
    -0.51
     streng
    -0.51
    POSITIVE LOGITS
     to
    0.94
    to
    0.80
    ucket
    0.64
    ¿
    0.63
     whether
    0.59
    nih
    0.57
    ²¾
    0.57
    ador
    0.57
    To
    0.55
     TO
    0.55
    Act Density 0.384%

    No Known Activations