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

    Neuronpedia

    INDEX
    Explanations

    the numerical values or identifiers often associated with significance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     onOptions
    -0.52
    гент
    -0.49
     Haut
    -0.47
    まして
    -0.47
    addPreferredGap
    -0.46
     base
    -0.44
     by
    -0.44
    ʲ
    -0.44
     Picchu
    -0.44
    brio
    -0.43
    POSITIVE LOGITS
     pleaſure
    0.74
    IntoConstraints
    0.69
    UserScript
    0.68
     ModelRenderer
    0.67
    guenos
    0.63
    asteroide
    0.63
    ContentAlignment
    0.63
     begge
    0.63
     pany
    0.61
    ؤلاء
    0.60
    Act Density 0.003%

    No Known Activations