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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orny
    -0.15
    gee
    -0.14
    ctal
    -0.14
    omba
    -0.14
    landa
    -0.14
    abaj
    -0.14
    USH
    -0.14
    urdy
    -0.13
    LEC
    -0.13
     اÙĦÙģر
    -0.13
    POSITIVE LOGITS
     Seas
    0.15
    oyer
    0.14
    variable
    0.14
     bev
    0.13
    harma
    0.13
    ruž
    0.13
    .protobuf
    0.13
    ond
    0.13
     Cody
    0.13
    att
    0.13
    Act Density 0.017%

    No Known Activations