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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and qualifiers that convey a sense of uncertainty or self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stk
    -0.16
     Hell
    -0.15
    inci
    -0.15
    alc
    -0.14
    juries
    -0.14
    wal
    -0.14
    _INCLUDED
    -0.14
    ÑĦÑĦ
    -0.14
    743
    -0.14
    agi
    -0.14
    POSITIVE LOGITS
    elsey
    0.17
    ruba
    0.16
    ackBar
    0.15
    ARRIER
    0.15
    ÅĻez
    0.14
    rase
    0.14
    oty
    0.14
    боÑĤ
    0.14
    aha
    0.14
    Boss
    0.13
    Act Density 0.044%

    No Known Activations