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

    Neuronpedia

    INDEX
    Explanations

    the name "Ph" followed by either random letters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term or concept "Ph."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -1.11
     fit
    -0.77
    PUT
    -0.77
    âĸ¬âĸ¬
    -0.76
     fitting
    -0.74
     Forth
    -0.70
    */(
    -0.70
     shortened
    -0.66
     Wink
    -0.66
    oldemort
    -0.65
    POSITIVE LOGITS
    osph
    1.44
    antom
    1.27
    oton
    1.20
    rase
    1.14
    ysics
    1.13
    ases
    1.12
    ummer
    1.11
    asing
    1.10
    armac
    1.09
    ilipp
    1.09
    Act Density 0.017%

    No Known Activations