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

    Neuronpedia

    INDEX
    Explanations

    words related to support or advocacy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rooting for teams or gambling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.87
    ibrary
    -0.86
    adian
    -0.86
    oxy
    -0.85
    inet
    -0.82
    ulic
    -0.80
    sam
    -0.78
    izo
    -0.78
    istic
    -0.77
    poral
    -0.76
    POSITIVE LOGITS
    CRIP
    0.82
     rooting
    0.79
     betting
    0.77
     passively
    0.74
    wana
    0.74
     Colomb
    0.73
     Rouse
    0.72
     Fans
    0.69
     bets
    0.68
     COVER
    0.68
    Act Density 0.015%

    No Known Activations