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

    Neuronpedia

    INDEX
    Explanations

    phrases about the struggle with understanding or articulating complex thoughts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Fns
    -0.56
    {}
    -0.48
    ıyla
    -0.43
    hyrchwyd
    -0.43
    ?
    -0.42
    >';
    -0.41
    Ранее
    -0.41
    ,
    -0.41
     upaya
    -0.41
     romanos
    -0.40
    POSITIVE LOGITS
    EDEFAULT
    0.85
    CppMethod
    0.80
    #
    0.79
    InSection
    0.74
    lapsingToolbar
    0.73
    UnusedPrivate
    0.71
     فريبيس
    0.70
    enderror
    0.70
     WaitForSeconds
    0.69
    SharedCtor
    0.69
    Act Density 0.016%

    No Known Activations