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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote a position or role, often using the word "as"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     تانيه
    -0.66
     متعلقه
    -0.66
     moulds
    -0.65
     smar
    -0.62
     ddelweddau
    -0.59
     mould
    -0.59
    Geplaatst
    -0.58
     ExecuteAsync
    -0.58
     freaks
    -0.57
    #!/
    -0.56
    POSITIVE LOGITS
    URIComponent
    0.66
    isome
    0.64
    erski
    0.63
    CellStyle
    0.63
    WithFormat
    0.60
    vieve
    0.60
    setVerticalGroup
    0.57
    kadang
    0.56
    ultuous
    0.56
     sederhana
    0.55
    Act Density 0.009%

    No Known Activations