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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical structures such as elevator shafts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of structural features and components related to construction or architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nap
    -0.90
    oleon
    -0.78
     Claire
    -0.69
     Cao
    -0.67
    Dispatch
    -0.66
     GOODMAN
    -0.65
    Ļ
    -0.64
     Lenn
    -0.63
     Conn
    -0.63
     Dum
    -0.62
    POSITIVE LOGITS
     shaft
    0.85
    owship
    0.83
    ithing
    0.81
    oaded
    0.81
    bent
    0.81
    lings
    0.81
    icular
    0.81
    itudinal
    0.80
    uded
    0.79
    ï¸ı
    0.78
    Act Density 0.021%

    No Known Activations