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

    Neuronpedia

    INDEX
    Explanations

    references to personality traits or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zoude
    -0.84
     desmotivaciones
    -0.73
     dezelve
    -0.70
     zelve
    -0.69
     templado
    -0.67
     navideño
    -0.65
     húmedo
    -0.64
     mijne
    -0.61
    umumkan
    -0.60
    berdayakan
    -0.60
    POSITIVE LOGITS
     pack
    0.63
     packs
    0.59
    beta
    0.57
     beta
    0.56
     Beta
    0.54
     Packs
    0.54
     Loop
    0.53
     tour
    0.51
     Pack
    0.49
     personalise
    0.49
    Act Density 0.473%

    No Known Activations