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

    Neuronpedia

    INDEX
    Explanations

    references to samples or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proport
    -0.16
    irty
    -0.16
    nish
    -0.16
    chemy
    -0.15
    atz
    -0.15
    atars
    -0.14
    Äį
    -0.14
    帯
    -0.14
    ÑĤий
    -0.14
    ackbar
    -0.13
    POSITIVE LOGITS
    abb
    0.16
    itan
    0.15
    arity
    0.15
    fare
    0.15
     plá
    0.14
     ngOn
    0.14
    iens
    0.14
    erman
    0.14
    ively
    0.14
    InOut
    0.14
    Act Density 0.007%

    No Known Activations