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

    Neuronpedia

    INDEX
    Explanations

    scholarly citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.60
    NECTION
    -0.58
    ----</
    -0.58
    Unmarshaller
    -0.51
    bootstrapcdn
    -0.50
     Accesat
    -0.48
    Награды
    -0.48
     various
    -0.47
    AndEndTag
    -0.47
    maxX
    -0.47
    POSITIVE LOGITS
    <bos>
    0.60
     betweenstory
    0.59
    +#+#
    0.55
    ModelForm
    0.55
    '},
    0.55
    //
    0.54
     médicale
    0.53
    dukan
    0.52
     commerciaux
    0.51
    TintMode
    0.51
    Act Density 0.164%

    No Known Activations