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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal reflection and evaluation of experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.85
    IntoConstraints
    -0.63
     RouterModule
    -0.61
    cloudfront
    -0.60
    UnusedPrivate
    -0.57
    CodeAttribute
    -0.54
     législation
    -0.53
    ngdoc
    -0.49
     bäst
    -0.48
     lunares
    -0.47
    POSITIVE LOGITS
    addElement
    0.75
    adə
    0.56
     var
    0.54
    مني
    0.54
    hObject
    0.54
    DMETHOD
    0.54
     Var
    0.53
    AMENTE
    0.52
    <%=
    0.50
     interact
    0.50
    Act Density 0.165%

    No Known Activations