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

    Neuronpedia

    INDEX
    Explanations

    words related to state or condition descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lic
    -0.15
    abile
    -0.15
    illas
    -0.14
    ustos
    -0.14
    utor
    -0.14
    onga
    -0.14
    Mahon
    -0.14
     Bom
    -0.14
    oute
    -0.14
    rous
    -0.14
    POSITIVE LOGITS
     precise
    0.18
     exact
    0.17
    exact
    0.17
    velt
    0.16
     Hedge
    0.16
     Byrne
    0.15
     precisely
    0.15
     ç²¾
    0.15
    ÑĤоÑĩ
    0.15
    gee
    0.15
    Act Density 0.002%

    No Known Activations