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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate additional information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.72
    ggles
    -0.70
    iste
    -0.66
    bis
    -0.64
    \\\\\\\\
    -0.63
     Founders
    -0.63
    aah
    -0.62
    anos
    -0.62
    der
    -0.60
    boys
    -0.60
    POSITIVE LOGITS
     thereto
    1.19
     to
    0.85
    ract
    0.74
    teness
    0.71
    ivity
    0.67
    ively
    0.66
    heid
    0.66
    ombat
    0.65
     ot
    0.63
    igm
    0.63
    Act Density 0.027%

    No Known Activations