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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating certainty or emphasis on a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    are
    -0.60
    ed
    -0.57
    able
    -0.56
    ,
    -0.55
    GEBURTS
    -0.49
     on
    -0.48
     with
    -0.47
     of
    -0.47
    ی
    -0.47
     from
    -0.46
    POSITIVE LOGITS
    alians
    0.87
     autorytatywna
    0.82
     habido
    0.78
     all
    0.76
     rained
    0.71
     snows
    0.70
    iner
    0.69
     fallu
    0.68
    ########.
    0.68
    inerary
    0.67
    Act Density 0.255%

    No Known Activations