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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.60
    OpenHelper
    -0.58
     stringBy
    -0.57
     wheelchair
    -0.56
     countless
    -0.56
     }}>
    -0.55
     Shaksp
    -0.54
     Poincaré
    -0.54
    !("
    -0.54
     Poincar
    -0.54
    POSITIVE LOGITS
    somewhat
    0.77
     somewhat
    0.75
    ISupport
    0.67
     Somewhat
    0.65
     المعيارى
    0.64
    Somewhat
    0.61
    有点
    0.61
     agak
    0.61
    有些不
    0.59
    antaine
    0.58
    Act Density 0.279%

    No Known Activations