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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting significant quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ternal
    -0.51
    hören
    -0.49
    нятно
    -0.46
    tron
    -0.45
     podjet
    -0.45
    cordia
    -0.44
    TagHelper
    -0.44
    うん
    -0.43
     port
    -0.43
    mpto
    -0.42
    POSITIVE LOGITS
    through
    0.95
    Through
    0.95
     through
    0.94
     hindurch
    0.93
    THROUGH
    0.90
     Through
    0.88
     THROUGH
    0.82
     attraverso
    0.73
     gjennom
    0.71
    を通して
    0.70
    Act Density 0.275%

    No Known Activations