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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.92
    хьтан
    -0.91
     Jefus
    -0.83
    .*")]
    -0.75
     Chrif
    -0.75
    principalTable
    -0.75
     sumpay
    -0.72
     iſt
    -0.72
    RenderAtEndOf
    -0.72
     pleaſure
    -0.71
    POSITIVE LOGITS
    <bos>
    0.71
    gesetzt
    0.53
    帖最后由
    0.49
     far
    0.47
    `
    0.46
     nó
    0.44
    }}}$
    0.43
    隧道
    0.42
     <<<<<<<<<<<<<<
    0.42
     may
    0.41
    Act Density 0.056%

    No Known Activations