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

    Neuronpedia

    INDEX
    Explanations

    modal adverbs indicating uncertainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.85
    px
    -0.72
    se
    -0.70
    en
    -0.66
     Tides
    -0.66
     veckor
    -0.64
     Birk
    -0.64
    tır
    -0.64
    WebControls
    -0.63
    ci
    -0.63
    POSITIVE LOGITS
    ✨:
    1.04
    mallows
    0.82
    selves
    0.82
    BibitemShut
    0.80
    fusc
    0.80
    hould
    0.80
    ciutto
    0.80
    ^(@)
    0.79
    BufferException
    0.77
     Loth
    0.75
    Act Density 0.097%

    No Known Activations