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

    Neuronpedia

    INDEX
    Explanations

    words related to lightness or illumination

    oai_token-act-pair · gpt-3.5-turbo

    words related to fighting or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APD
    -0.75
    ãĤª
    -0.73
    berman
    -0.73
    Interstitial
    -0.65
    ãĥ¡
    -0.64
    ש
    -0.61
    ching
    -0.61
    anium
    -0.60
     à¤
    -0.59
    tering
    -0.58
    POSITIVE LOGITS
    uilt
    0.91
    itage
    0.84
    mares
    0.84
    eous
    0.83
    ighth
    0.81
    ield
    0.80
    ouston
    0.77
    ouse
    0.76
    cffff
    0.74
    shire
    0.73
    Act Density 0.008%

    No Known Activations