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

    Neuronpedia

    INDEX
    Explanations

    terms related to relative comparisons or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelForm
    -0.56
     in
    -0.54
    ,
    -0.53
     –
    -0.53
    !
    -0.52
     plan
    -0.51
     local
    -0.51
    /
    -0.51
     (
    -0.49
    :
    -0.48
    POSITIVE LOGITS
    Aiheesta
    0.89
     resourceCulture
    0.87
     ſever
    0.86
    expandindo
    0.85
     auffi
    0.85
     Audiodateien
    0.83
     raiſ
    0.83
     ſel
    0.82
     purpoſe
    0.81
     المعيارى
    0.80
    Act Density 0.281%

    No Known Activations