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

    Neuronpedia

    INDEX
    Explanations

    instances of performance-related actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.17
    uÄį
    -0.16
     pw
    -0.15
    tok
    -0.15
    haar
    -0.15
    ån
    -0.15
    odb
    -0.15
    undle
    -0.14
    sy
    -0.14
     PW
    -0.14
    POSITIVE LOGITS
    æ´²
    0.16
    ì°©
    0.15
    inos
    0.15
    Perform
    0.14
    uhe
    0.14
    .hxx
    0.14
    perform
    0.14
    lopedia
    0.14
    èĺ
    0.13
    æ¡ij
    0.13
    Act Density 0.081%

    No Known Activations