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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and interactions among characters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     voudrais
    -0.56
    __(/*!
    -0.52
    :%.
    -0.52
    })).
    -0.50
     fú
    -0.50
     vogli
    -0.49
     unarmed
    -0.49
     immédi
    -0.48
    ))).
    -0.48
    FOC
    -0.48
    POSITIVE LOGITS
     nod
    0.72
     sigh
    0.70
     '\\;'
    0.69
     Sigh
    0.65
     Nod
    0.61
    sighs
    0.61
    ikiki
    0.61
     nudge
    0.60
     noDo
    0.60
    anuts
    0.60
    Act Density 0.042%

    No Known Activations