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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate conditional agreements or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quin
    -0.15
    opathy
    -0.15
    çĶº
    -0.14
    obili
    -0.14
    erp
    -0.14
    eras
    -0.14
    æĤł
    -0.14
    tod
    -0.14
    ey
    -0.14
    ESIS
    -0.14
    POSITIVE LOGITS
    endi
    0.28
    ulation
    0.25
    ple
    0.25
    pled
    0.24
    end
    0.23
    ulations
    0.22
    ulated
    0.22
    ulate
    0.22
    ends
    0.20
    PLE
    0.20
    Act Density 0.006%

    No Known Activations