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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "victor" or "victim"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¤
    -0.18
    otion
    -0.16
    osc
    -0.15
    205
    -0.15
    fter
    -0.14
    ITIES
    -0.14
    ishment
    -0.14
    seau
    -0.14
    head
    -0.14
    Indexed
    -0.14
    POSITIVE LOGITS
    ims
    0.28
    orious
    0.28
    orian
    0.27
    imizer
    0.26
    oriously
    0.26
    imized
    0.25
    ory
    0.25
    oire
    0.25
    ories
    0.25
    imization
    0.24
    Act Density 0.005%

    No Known Activations