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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of doubt or debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĬØ«
    -0.15
     Heller
    -0.15
    IFA
    -0.15
    ÅĽcie
    -0.15
    volt
    -0.15
    ãĥĭãĤ¢
    -0.14
    addle
    -0.14
    orrar
    -0.14
    rand
    -0.14
    ITA
    -0.14
    POSITIVE LOGITS
    addock
    0.17
    èĨ
    0.15
    udos
    0.15
     merc
    0.14
     Mercy
    0.14
    iger
    0.14
    داÙħ
    0.14
     Merc
    0.14
    _compress
    0.14
    amac
    0.13
    Act Density 0.149%

    No Known Activations