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

    Neuronpedia

    INDEX
    Explanations

    descriptors of smoothness and fluidity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apia
    -0.15
    .gdx
    -0.15
    aggi
    -0.15
    agara
    -0.14
    ãĥ©ãĤ¤ãĥĪ
    -0.14
    ACT
    -0.13
    utherford
    -0.13
    acting
    -0.13
    AuthGuard
    -0.13
    perature
    -0.13
    POSITIVE LOGITS
    454
    0.15
    íķĻê³¼
    0.15
    ãĤ¦ãĥ³
    0.15
    (er
    0.14
    edy
    0.14
    est
    0.14
    SIDE
    0.14
    ctors
    0.14
    ery
    0.14
    rew
    0.14
    Act Density 0.017%

    No Known Activations