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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intended action

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </i>
    -0.57
     in
    -0.55
     as
    -0.54
     get
    -0.53
     .
    -0.53
     even
    -0.53
     effectively
    -0.52
     Majesté
    -0.51
     destra
    -0.50
    mbrie
    -0.49
    POSITIVE LOGITS
     Audiodateien
    1.02
    enumi
    0.95
     CreateTagHelper
    0.93
     ProtoMessage
    0.90
     reaſon
    0.88
     ostavi
    0.85
     Efq
    0.84
    protoimpl
    0.84
     reafon
    0.82
     חיצוניים
    0.81
    Act Density 0.013%

    No Known Activations