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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Phil" and related terms indicating philanthropy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uala
    -0.19
    rous
    -0.18
    yms
    -0.15
    ionales
    -0.15
    elta
    -0.15
    ception
    -0.15
    ety
    -0.14
    esta
    -0.14
    ette
    -0.14
    LastError
    -0.14
    POSITIVE LOGITS
    ipp
    0.33
    ippi
    0.26
    ippines
    0.26
    omen
    0.26
    osopher
    0.25
    osoph
    0.24
    istine
    0.24
    ipe
    0.23
    adelphia
    0.22
    andering
    0.22
    Act Density 0.007%

    No Known Activations