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

    Neuronpedia

    INDEX
    Explanations

    words related to celestial bodies, specifically comets

    oai_token-act-pair · gpt-3.5-turbo

    references to comets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skirts
    -0.83
    dos
    -0.76
    radical
    -0.73
    yrinth
    -0.73
    stood
    -0.71
    antha
    -0.69
    Hispanic
    -0.65
    lied
    -0.65
    ieval
    -0.65
    ames
    -0.65
    POSITIVE LOGITS
     comet
    1.10
     Ping
    0.81
     nucleus
    0.75
     Chaser
    0.75
     Comet
    0.75
     Nebula
    0.71
     tails
    0.70
     logo
    0.65
     crater
    0.65
    hedral
    0.65
    Act Density 0.007%

    No Known Activations