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

    Neuronpedia

    INDEX
    Explanations

    temporal markers and expressions of conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -tm
    -0.18
    etur
    -0.15
    yna
    -0.15
    ãĤī
    -0.15
    лам
    -0.15
    munition
    -0.15
    MAND
    -0.15
    raci
    -0.14
    .Focused
    -0.14
    _VIRTUAL
    -0.14
    POSITIVE LOGITS
    ava
    0.16
    vest
    0.15
     ref
    0.15
     flo
    0.14
    tones
    0.14
    est
    0.14
     ware
    0.13
    ùi
    0.13
    less
    0.13
    burg
    0.13
    Act Density 0.240%

    No Known Activations