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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "called" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Contr
    -0.62
     Prov
    -0.58
     Ori
    -0.57
     Explor
    -0.56
     xls
    -0.54
     Prof
    -0.53
     colle
    -0.52
    holl
    -0.50
     Expl
    -0.50
     prof
    -0.50
    POSITIVE LOGITS
    called
    1.09
    Called
    0.98
     llamado
    0.98
     llamada
    0.94
     called
    0.90
     Called
    0.90
     CALLED
    0.87
     chamado
    0.86
     chamada
    0.86
     llamados
    0.85
    Act Density 0.206%

    No Known Activations