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

    Neuronpedia

    INDEX
    Explanations

    expressions of humor and personal traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſte
    -0.47
    帖最后由
    -0.43
    Erstellt
    -0.40
     neceff
    -0.40
     suffic
    -0.40
     fatis
    -0.40
     sust
    -0.39
     Succes
    -0.39
     ſtand
    -0.39
     itſelf
    -0.39
    POSITIVE LOGITS
     charisma
    0.89
     ability
    0.88
     sense
    0.85
     personality
    0.80
     penchant
    0.79
     knack
    0.77
     uncanny
    0.74
     charm
    0.73
     infectious
    0.72
     talents
    0.70
    Act Density 0.287%

    No Known Activations