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

    Neuronpedia

    INDEX
    Explanations

    phrases or structures indicating statements or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consolidated
    -0.15
     Nagar
    -0.15
     sake
    -0.14
    elivery
    -0.14
    IGHL
    -0.14
    446
    -0.14
     nor
    -0.14
    ediator
    -0.13
    ULO
    -0.13
    _$_
    -0.13
    POSITIVE LOGITS
    rief
    0.20
    té
    0.17
    lue
    0.16
    гл
    0.15
    ħ§
    0.15
    ulle
    0.15
    chy
    0.14
    ANGLES
    0.14
    ewidth
    0.14
    serie
    0.14
    Act Density 0.019%

    No Known Activations