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

    Neuronpedia

    INDEX
    Explanations

    references to questionnaires, lists, and articles related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
     كومونز
    -0.63
    ScopeManager
    -0.60
     متعلقه
    -0.59
    ftagPool
    -0.55
     ligiloj
    -0.54
     queſta
    -0.54
     mergeFrom
    -0.54
    SourceChecksum
    -0.52
    ğraf
    -0.52
    POSITIVE LOGITS
    eseorang
    0.44
     angefü
    0.38
     góry
    0.35
    iging
    0.35
    unggah
    0.35
    click
    0.35
    éně
    0.35
     below
    0.34
     click
    0.34
     omge
    0.33
    Act Density 0.477%

    No Known Activations