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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases or clauses that engage the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tol
    -0.17
    è°±
    -0.16
     ÙĨظ
    -0.15
    Bars
    -0.15
    omu
    -0.15
    tura
    -0.15
    loat
    -0.15
    adil
    -0.15
     æļ
    -0.14
    echa
    -0.14
    POSITIVE LOGITS
     J
    0.17
    oui
    0.15
     Kiss
    0.15
    ss
    0.15
    rc
    0.14
     substr
    0.14
    inka
    0.14
    _unpack
    0.14
     Anchor
    0.13
    225
    0.13
    Act Density 0.001%

    No Known Activations