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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "manner," "extent," or "rate" followed by "in/to/at/of"

    np_acts-logits-general · gemini-2.0-flash

    manner, extent, way, rate, means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.89
     Monfieur
    -0.86
    __(/*!
    -0.82
     Majefty
    -0.81
     Efq
    -0.80
     becauſe
    -0.77
     Jefus
    -0.75
     pleaſure
    -0.75
     himſelf
    -0.75
     faſt
    -0.74
    POSITIVE LOGITS
     which
    1.26
     waarin
    1.20
    which
    0.93
     wherein
    0.93
     waarop
    0.90
     cui
    0.90
     where
    0.89
     whereby
    0.86
     Which
    0.85
     auquel
    0.82
    Act Density 0.287%

    No Known Activations