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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions and disclaiming representation of those opinions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     createState
    -0.50
    httphttps
    -0.47
    Infer
    -0.42
    eben
    -0.41
    strum
    -0.41
    Revenir
    -0.40
     unauthorised
    -0.40
    出版年
    -0.40
     video
    -0.40
    ario
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.82
    WillAppear
    0.75
    featureID
    0.70
    signee
    0.66
     doubtnut
    0.65
    setof
    0.63
    phalt
    0.63
    regated
    0.63
    engertian
    0.61
     comigo
    0.60
    Act Density 0.005%

    No Known Activations