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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations, approvals, and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    way
    -0.15
    us
    -0.15
    ins
    -0.15
    628
    -0.15
    emes
    -0.14
    po
    -0.14
     Garland
    -0.14
     propensity
    -0.14
    els
    -0.14
    ver
    -0.14
    POSITIVE LOGITS
    cheid
    0.17
    .TextAlignment
    0.15
    opyright
    0.15
    ndon
    0.14
    elps
    0.14
    lut
    0.14
    isory
    0.14
    [source
    0.14
    lund
    0.14
    itant
    0.14
    Act Density 0.096%

    No Known Activations