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

    Neuronpedia

    INDEX
    Explanations

    phrases related to setting things aside or putting them on hold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĩ
    -0.15
    Ùİج
    -0.14
    onec
    -0.14
    ÑģÑĮого
    -0.14
    acker
    -0.14
    statt
    -0.14
    ROADCAST
    -0.14
    _hub
    -0.13
    .createServer
    -0.13
    icz
    -0.13
    POSITIVE LOGITS
     aside
    0.93
    aside
    0.75
     Aside
    0.66
    Aside
    0.58
     apart
    0.47
     side
    0.39
     besides
    0.39
    side
    0.35
     Apart
    0.35
     Side
    0.33
    Act Density 0.102%

    No Known Activations