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

    Neuronpedia

    INDEX
    Explanations

    references to heavy objects or intense experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
    Tikang
    -0.67
    ThroughAttribute
    -0.67
    TemporalType
    -0.60
     Administrativna
    -0.55
    rapie
    -0.54
    MetaObject
    -0.53
    olella
    -0.53
    fürst
    -0.53
    actionMode
    -0.52
    POSITIVE LOGITS
     heavy
    0.86
    heavy
    0.80
     Heavy
    0.80
    Heavy
    0.80
     pesada
    0.78
     heavier
    0.74
     HEAVY
    0.74
     heaviest
    0.70
    重
    0.70
     weight
    0.69
    Act Density 2.678%

    No Known Activations