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

    Neuronpedia

    INDEX
    Explanations

    references to indirect implications and subtleties in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egov
    -0.17
    rum
    -0.16
    iales
    -0.16
    egade
    -0.16
    /jav
    -0.15
     hạng
    -0.14
    remember
    -0.14
    祥
    -0.14
    ardon
    -0.14
    FileVersion
    -0.14
    POSITIVE LOGITS
     dust
    0.16
    077
    0.15
    VEL
    0.15
     fluids
    0.15
     Dust
    0.14
     lim
    0.14
     vel
    0.14
    078
    0.14
    ync
    0.13
     forbidden
    0.13
    Act Density 0.139%

    No Known Activations