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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "though."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     PLW
    -0.76
     Hald
    -0.75
     Merz
    -0.71
    makeConstraints
    -0.71
    enlace
    -0.71
    hematical
    -0.70
     rejoicing
    -0.70
    mappedBy
    -0.69
     Lur
    -0.69
     Tj
    -0.69
    POSITIVE LOGITS
     تانيه
    0.82
    '])->
    0.80
    aughan
    0.74
    optString
    0.71
     Wynne
    0.68
     }}"></
    0.67
    TypedValue
    0.66
     Phipps
    0.65
     sī
    0.65
     Woodbridge
    0.65
    Act Density 0.011%

    No Known Activations