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

    Neuronpedia

    INDEX
    Explanations

    references to actions involving a group or team

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saddle
    -0.77
    urally
    -0.76
    ises
    -0.71
     prints
    -0.67
     Papers
    -0.65
    ittle
    -0.64
     materials
    -0.64
     decks
    -0.63
     stationary
    -0.62
    ident
    -0.62
    POSITIVE LOGITS
    ova
    0.92
    FBI
    0.82
    Story
    0.79
    antha
    0.77
    ãĤ´ãĥ³
    0.77
    advertising
    0.77
     Liberties
    0.76
    bleacher
    0.74
    ults
    0.74
    yahoo
    0.74
    Act Density 0.000%

    No Known Activations