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

    Neuronpedia

    INDEX
    Explanations

    negation or phrases indicating opposition or disagreement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    juvant
    -0.62
    CJK
    -0.60
    жели
    -0.57
    corrhi
    -0.57
     Aesthetics
    -0.52
    вня
    -0.51
    ibald
    -0.50
     Üniversitesi
    -0.50
    esthetics
    -0.50
    imals
    -0.49
    POSITIVE LOGITS
     Roskov
    0.84
    LookAnd
    0.77
    rungsseite
    0.72
    SourceChecksum
    0.67
    +#+#
    0.66
    RTEX
    0.64
    OGND
    0.63
     متعلقه
    0.63
    الإنجليزية
    0.62
     CreateTagHelper
    0.62
    Act Density 0.005%

    No Known Activations