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

    Neuronpedia

    INDEX
    Explanations

    the possessive form of team names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tours
    -0.65
     RN
    -0.63
     Stuff
    -0.60
     Detail
    -0.60
     Rothschild
    -0.60
     Alexandria
    -0.60
     Lur
    -0.60
     Hasan
    -0.59
     Sinn
    -0.59
     Yard
    -0.58
    POSITIVE LOGITS
    lightly
    1.39
    omew
    1.27
    uddenly
    1.26
    pecially
    1.21
    atisf
    1.21
    ELF
    1.21
    outhern
    1.19
    aturated
    1.18
    aying
    1.17
    keleton
    1.17
    Act Density 0.184%

    No Known Activations