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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that indicate a special or significant quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzle
    -0.16
    croft
    -0.16
    cry
    -0.15
    uhn
    -0.15
    wnd
    -0.15
    ide
    -0.15
    lide
    -0.14
    ÑĤом
    -0.14
    HING
    -0.14
    iciel
    -0.14
    POSITIVE LOGITS
    oteric
    0.27
    pecially
    0.24
    ophage
    0.22
    SENT
    0.19
    prit
    0.19
    ENTIAL
    0.18
    _ES
    0.17
    sex
    0.17
    oter
    0.17
    ablish
    0.17
    Act Density 0.016%

    No Known Activations