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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical analysis and data metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "by" or "with"

    np_acts-logits-general · gemini-2.0-flash

    by or with followed by a noun or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.86
    VersionUID
    -0.76
     Majefty
    -0.76
    ValueStyle
    -0.76
    CloseOperation
    -0.75
     houſe
    -0.75
     itſelf
    -0.71
     Monfieur
    -0.70
    انيف
    -0.68
     ſche
    -0.68
    POSITIVE LOGITS
     using
    0.60
     which
    0.53
     folos
    0.51
     cual
    0.51
     apporté
    0.49
     utilizing
    0.49
     utilisant
    0.47
     menggunakan
    0.47
    elp
    0.46
     pomocou
    0.46
    Act Density 0.306%

    No Known Activations