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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration or noteworthy qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Holman
    -0.74
     coluna
    -0.59
     Normdatei
    -0.59
    SPJ
    -0.56
     généraux
    -0.56
    ImageContext
    -0.56
    Och
    -0.54
     Fielding
    -0.54
    zeman
    -0.52
    PathVariable
    -0.52
    POSITIVE LOGITS
    Impressive
    1.61
     impress
    1.43
     Impressive
    1.41
     impressed
    1.37
     impressive
    1.24
     myſelf
    1.16
     itſelf
    1.16
     impres
    1.15
     himſelf
    1.08
     unimp
    1.03
    Act Density 0.005%

    No Known Activations