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

    Neuronpedia

    INDEX
    Explanations

    Phrases or terms related to academic titles or achievements

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "Ph" typically related to academic degrees or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.97
     fit
    -0.75
    */(
    -0.73
    PUT
    -0.73
     stroke
    -0.71
     fitting
    -0.70
    âĸ¬âĸ¬
    -0.67
     Stro
    -0.66
     shortened
    -0.66
     Forth
    -0.65
    POSITIVE LOGITS
    osph
    1.49
    antom
    1.18
    rase
    1.17
    ases
    1.17
    asing
    1.14
    ysics
    1.13
    oton
    1.12
    ummer
    1.09
    armac
    1.08
    aser
    1.07
    Act Density 0.014%

    No Known Activations