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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or concepts associated with technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    polation
    -0.93
    iffance
    -0.93
     Efq
    -0.91
    ollary
    -0.91
    arote
    -0.91
     Theſe
    -0.88
    ratulations
    -0.87
    ousand
    -0.86
    BibitemShut
    -0.85
    encils
    -0.84
    POSITIVE LOGITS
    -
    1.01
    out
    0.60
    al
    0.57
    ISupport
    0.54
    M
    0.54
    ri
    0.54
    ie
    0.54
    _
    0.53
    T
    0.52
    re
    0.52
    Act Density 0.318%

    No Known Activations