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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate naming or defining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.61
    OrBuilder
    -0.56
    Dimanche
    -0.51
    ditto
    -0.51
    EClass
    -0.50
     dup
    -0.50
     να
    -0.49
     πισ
    -0.49
    prüche
    -0.48
    charCodeAt
    -0.48
    POSITIVE LOGITS
     called
    0.76
     CALLED
    0.74
    叫做
    0.72
    Tembelea
    0.72
    called
    0.71
    UnknownFieldSet
    0.71
     chiamata
    0.71
     éduc
    0.70
    Called
    0.70
     chiamato
    0.70
    Act Density 0.136%

    No Known Activations