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

    Neuronpedia

    INDEX
    Explanations

    specific letter patterns or sequences within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceous
    -0.17
    ream
    -0.17
    peater
    -0.16
    ARGIN
    -0.15
    irsch
    -0.15
    oud
    -0.15
    placer
    -0.15
    EDIUM
    -0.14
    ãģįãģŁ
    -0.14
    occan
    -0.14
    POSITIVE LOGITS
    s
    0.20
    -vous
    0.20
    illow
    0.19
    illions
    0.18
    ephy
    0.18
    ephir
    0.18
    abbix
    0.18
    zy
    0.18
    ãĤ©
    0.17
    (es
    0.17
    Act Density 0.378%

    No Known Activations