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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations and municipalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.77
    UnsafeEnabled
    -0.64
    EDEFAULT
    -0.61
    rån
    -0.58
     aikana
    -0.58
     الاطلاع
    -0.56
     certes
    -0.56
    IsContent
    -0.56
    IENCE
    -0.55
    rrggbb
    -0.55
    POSITIVE LOGITS
     purpoſe
    0.67
     Majefty
    0.66
     ſeveral
    0.63
    ########.
    0.63
     ſtand
    0.61
     Theſe
    0.60
    ſelf
    0.59
     becauſe
    0.59
     Houſe
    0.58
    ſelves
    0.57
    Act Density 0.303%

    No Known Activations