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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "unless."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     /\.(
    -0.72
     Савезне
    -0.70
     pinulongan
    -0.69
    rungsseite
    -0.64
    WireFormatLite
    -0.60
    kloped
    -0.60
    ANDUM
    -0.60
    참고
    -0.60
     colspan
    -0.59
    Jegyzetek
    -0.59
    POSITIVE LOGITS
     clôture
    0.53
     soffer
    0.47
    บู
    0.46
     renouvel
    0.44
    Close
    0.44
    limus
    0.44
    rija
    0.41
    close
    0.41
    eleste
    0.41
    ^{*}=
    0.41
    Act Density 0.001%

    No Known Activations