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

    Neuronpedia

    INDEX
    Explanations

    key terms related to processes or conditions that suggest stability or permanence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vox
    -0.14
     bulletin
    -0.14
    cz
    -0.14
    icity
    -0.14
    aft
    -0.13
    imony
    -0.13
     Vanguard
    -0.13
     handjob
    -0.13
     Cop
    -0.13
    зна
    -0.13
    POSITIVE LOGITS
    urope
    0.16
    atoria
    0.15
    arth
    0.15
    erno
    0.14
     Quad
    0.14
    orro
    0.14
    CI
    0.14
    inces
    0.14
    bic
    0.13
    ulo
    0.13
    Act Density 0.036%

    No Known Activations