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

    Neuronpedia

    INDEX
    Explanations

    specific attributes or characteristics related to products and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.93
     Efq
    -0.86
     defaultstate
    -0.85
    TintMode
    -0.85
     Monfieur
    -0.82
    ISupport
    -0.80
     pleaſure
    -0.79
     Chriftian
    -0.78
     beſt
    -0.77
    UnsafeEnabled
    -0.77
    POSITIVE LOGITS
     specific
    0.55
     tertentu
    0.54
    less
    0.51
     differ
    0.48
     vary
    0.48
     not
    0.48
    별
    0.47
     different
    0.47
     depend
    0.44
    =
    0.43
    Act Density 0.672%

    No Known Activations