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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    s
    -1.06
    $​
    -0.67
     mers
    -0.65
    constructor
    -0.60
     Camus
    -0.59
     zaidi
    -0.58
     asemenea
    -0.57
     greu
    -0.57
     in
    -0.57
    gendes
    -0.56
    POSITIVE LOGITS
    InjectAttribute
    1.13
    complexContent
    0.95
    UIControlState
    0.90
    Thank
    0.89
     Thank
    0.89
     nakalista
    0.88
    ExtendWith
    0.88
    Slf
    0.87
    NewUrlParser
    0.86
    +#+
    0.84
    Act Density 0.005%

    No Known Activations