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

    Neuronpedia

    INDEX
    Explanations

    actions related to research and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PointerException
    -0.16
    dea
    -0.15
    agrid
    -0.15
    opus
    -0.15
    ниÑĨÑĮ
    -0.14
    entai
    -0.14
    .Unity
    -0.14
    ewis
    -0.14
     Hlav
    -0.14
    deaux
    -0.13
    POSITIVE LOGITS
    ħn
    0.19
    ked
    0.16
    etri
    0.14
     Jab
    0.14
    389
    0.14
    erin
    0.14
    theid
    0.13
    ansen
    0.13
    hausen
    0.13
    Wh
    0.13
    Act Density 0.161%

    No Known Activations