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

    Neuronpedia

    INDEX
    Explanations

    words related to actions taken by individuals or groups within narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     समीक्षाएं
    -0.76
     kasarigan
    -0.73
    Datuak
    -0.71
    Personendaten
    -0.69
     Réponses
    -0.62
    ConstraintMaker
    -0.61
    ArgsConstructor
    -0.58
     autorytatywna
    -0.57
     ILS
    -0.54
     Signor
    -0.53
    POSITIVE LOGITS
     me
    0.73
     us
    0.59
     Grossman
    0.57
    PDIR
    0.56
    insegna
    0.55
     gave
    0.53
     tặng
    0.53
    esistenza
    0.52
     gratuitement
    0.51
     gratuits
    0.51
    Act Density 0.502%

    No Known Activations