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

    Neuronpedia

    INDEX
    Explanations

    references to the word "untitled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.16
    ÙģØ©
    -0.16
    eking
    -0.15
    Ñıж
    -0.15
    SEC
    -0.15
    uchi
    -0.14
    ULA
    -0.14
    VICE
    -0.14
    _nsec
    -0.14
    abort
    -0.14
    POSITIVE LOGITS
     unt
    0.25
    itled
    0.24
    ainted
    0.20
     Unt
    0.19
    oten
    0.19
    untu
    0.17
    old
    0.17
    amed
    0.17
    ouched
    0.17
    ouch
    0.16
    Act Density 0.005%

    No Known Activations