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

    Neuronpedia

    INDEX
    Explanations

    references to experimental studies or research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     espagne
    -0.69
    SerializedName
    -0.67
     uſe
    -0.66
     démocr
    -0.63
    Xaml
    -0.63
     raiſ
    -0.63
     anſ
    -0.61
     ferons
    -0.61
    hoea
    -0.60
     survie
    -0.60
    POSITIVE LOGITS
    ען
    0.57
     collaborators
    0.57
    enumi
    0.55
    jne
    0.54
    SourceChecksum
    0.54
     collaborator
    0.54
    ]-'
    0.54
     collab
    0.52
     collaborated
    0.50
    toy
    0.49
    Act Density 0.099%

    No Known Activations