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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey performance evaluation and character dynamics in film

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     functools
    -0.50
    istoitu
    -0.48
     desain
    -0.48
     tiện
    -0.46
     poire
    -0.45
     faim
    -0.44
     corte
    -0.43
     ripar
    -0.43
    Varint
    -0.43
    Enllaços
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.69
    <bos>
    0.67
     dialects
    0.67
    ⓧ
    0.63
     convincingly
    0.61
    0.60
    vábbi
    0.59
    mals
    0.56
    avadoc
    0.56
     octave
    0.56
    Act Density 0.031%

    No Known Activations