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

    Neuronpedia

    INDEX
    Explanations

    statistical terminology related to mean and error calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortawesome
    -0.64
    tagHelperRunner
    -0.57
    -0.56
    󠁢
    -0.47
    Bakgrunnsstoff
    -0.46
    featureID
    -0.45
    ########.
    -0.45
    providedIn
    -0.44
    pencer
    -0.42
    anganese
    -0.41
    POSITIVE LOGITS
     literalmente
    0.59
     exactly
    0.56
     literally
    0.56
    fulness
    0.55
     spirited
    0.54
    urement
    0.52
    spirited
    0.50
    lessness
    0.49
     litté
    0.49
    tioned
    0.49
    Act Density 0.142%

    No Known Activations