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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reasoning and motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ize
    -0.17
    ird
    -0.16
     tomorrow
    -0.16
     laps
    -0.15
    /comment
    -0.15
     cache
    -0.15
     geometry
    -0.14
    cache
    -0.14
     inheritance
    -0.14
     U
    -0.14
    POSITIVE LOGITS
    ffen
    0.16
    uisse
    0.16
    eri
    0.16
    utos
    0.16
    zend
    0.16
    ãģĵãģĿ
    0.16
    ÑĪин
    0.16
    skyt
    0.15
    edException
    0.15
    ippy
    0.15
    Act Density 0.379%

    No Known Activations