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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /\.(
    -0.80
     Roskov
    -0.74
    XtraBars
    -0.73
    loài
    -0.72
     tartalomajánló
    -0.71
    Xna
    -0.70
    clientY
    -0.69
    yelitis
    -0.69
    viaf
    -0.67
    setVerticalGroup
    -0.67
    POSITIVE LOGITS
     grateful
    1.15
     glad
    1.10
     pleased
    1.07
     afraid
    1.04
     impressed
    0.98
     thrilled
    0.96
     delighted
    0.96
     thankful
    0.96
     scared
    0.96
     frightened
    0.96
    Act Density 0.138%

    No Known Activations