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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movements or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "mb" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.84
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
    zona
    -0.71
    apons
    -0.68
    aways
    -0.64
    ources
    -0.62
    ãĥ´ãĤ¡
    -0.62
    come
    -0.61
    ttes
    -0.61
    ãĥ³ãĤ¸
    -0.60
    POSITIVE LOGITS
    iotic
    1.11
    ilib
    1.07
    uild
    1.04
    iotics
    0.99
    edded
    0.99
    iosis
    0.98
    odies
    0.97
    olicy
    0.93
    arrass
    0.88
    ortal
    0.87
    Act Density 0.014%

    No Known Activations