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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to data points or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تعدى
    -0.82
    setcounter
    -0.81
    CascadeType
    -0.74
    cloudfront
    -0.74
     PCC
    -0.71
     виправивши
    -0.70
    riors
    -0.70
    lamabad
    -0.69
     lus
    -0.68
    iop
    -0.68
    POSITIVE LOGITS
     erb
    0.70
    팎
    0.70
    ValueStyle
    0.65
     retra
    0.64
     vmax
    0.63
     EMB
    0.62
    thyst
    0.60
    ResponseEntity
    0.60
     Kela
    0.58
    ingway
    0.58
    Act Density 0.251%

    No Known Activations