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

    Neuronpedia

    INDEX
    Explanations

    positive and negative evaluations of situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpt
    -0.16
    bows
    -0.15
    idy
    -0.14
    ebin
    -0.14
    apsed
    -0.14
    xAF
    -0.14
    assen
    -0.14
    або
    -0.14
    opi
    -0.14
    íĦ
    -0.14
    POSITIVE LOGITS
    agger
    0.15
    hen
    0.15
    umat
    0.14
     indefinite
    0.14
    uni
    0.14
    Uni
    0.14
    icies
    0.14
     Liberties
    0.14
    ooke
    0.14
    TEL
    0.13
    Act Density 0.134%

    No Known Activations