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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vej
    -0.14
    zá
    -0.14
    .Plugin
    -0.14
    avigator
    -0.14
    haar
    -0.13
    ظÙĩ
    -0.13
    odia
    -0.13
    uish
    -0.13
    ookie
    -0.13
     whereas
    -0.13
    POSITIVE LOGITS
    iero
    0.16
     Hers
    0.15
    å
    0.14
    DataSetChanged
    0.14
     hell
    0.14
    AYS
    0.14
    INGER
    0.13
     Oro
    0.13
     ey
    0.13
    ey
    0.13
    Act Density 0.384%

    No Known Activations