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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or terms in explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     from
    -0.54
     that
    -0.53
    /
    -0.48
    正文
    -0.47
     serata
    -0.46
    WriteTagHelper
    -0.46
    RTEX
    -0.46
     those
    -0.46
     (?)
    -0.45
     —
    -0.45
    POSITIVE LOGITS
     latter
    1.04
     way
    0.84
     kind
    0.82
     particular
    0.81
     information
    0.77
    latter
    0.76
     derniers
    0.74
     type
    0.73
     feature
    0.71
     section
    0.70
    Act Density 0.462%

    No Known Activations