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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of professional transitions and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ware
    -0.16
    toFloat
    -0.15
    asley
    -0.15
    .raises
    -0.15
    iders
    -0.15
    elden
    -0.15
    á»IJ
    -0.15
    generic
    -0.14
    á»ĭ
    -0.14
    ska
    -0.14
    POSITIVE LOGITS
     unused
    0.17
    á»ĵng
    0.16
     Unused
    0.15
     dependent
    0.15
     sins
    0.14
    aky
    0.14
    stateParams
    0.14
     indef
    0.14
    /component
    0.14
    rollo
    0.13
    Act Density 0.439%

    No Known Activations