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

    Neuronpedia

    INDEX
    Explanations

    words related to indicating or signaling something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.16
    232
    -0.15
    ync
    -0.15
    KeyEvent
    -0.15
    StateToProps
    -0.15
    аÑİ
    -0.15
    BOSE
    -0.14
    ãĥ¼ãĥ©
    -0.14
    leigh
    -0.14
    orts
    -0.14
    POSITIVE LOGITS
    atures
    0.23
    ificance
    0.23
    ificantly
    0.23
    ificant
    0.18
    reed
    0.17
    atories
    0.17
    posted
    0.16
    SIGN
    0.15
    sd
    0.15
    nature
    0.15
    Act Density 0.038%

    No Known Activations