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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific times or situations in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.17
    olutely
    -0.17
    ç¾
    -0.15
    dden
    -0.15
    ancellor
    -0.15
    quired
    -0.15
    .sg
    -0.14
    otten
    -0.14
    cheid
    -0.14
    rike
    -0.14
    POSITIVE LOGITS
     weekends
    0.23
     Weekend
    0.17
     grass
    0.16
     stage
    0.16
    _reporting
    0.15
     Persistence
    0.15
    Fcn
    0.15
     Hayward
    0.14
    zes
    0.14
     weekend
    0.14
    Act Density 0.113%

    No Known Activations