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

    Neuronpedia

    INDEX
    Explanations

    references to astronomical objects, specifically comets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skirts
    -0.88
    dos
    -0.76
    uckland
    -0.76
    lasses
    -0.70
    otics
    -0.69
    antha
    -0.69
    imm
    -0.68
    radical
    -0.68
    ames
    -0.63
    Hispanic
    -0.63
    POSITIVE LOGITS
     comet
    0.99
     Ping
    0.91
     nucleus
    0.79
     tails
    0.74
     Pluto
    0.69
     Comet
    0.69
     crater
    0.69
    hedral
    0.69
     crust
    0.66
     orbiting
    0.66
    Act Density 0.017%

    No Known Activations