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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NEVER
    -0.16
    tering
    -0.16
    UNKNOWN
    -0.15
    Never
    -0.15
     olmayan
    -0.15
    never
    -0.15
     Never
    -0.15
    alim
    -0.15
    -pills
    -0.15
    ัà¸ĩà¹Ħม
    -0.15
    POSITIVE LOGITS
     note
    0.25
     not
    0.24
     now
    0.23
     whether
    0.23
     nah
    0.23
     nor
    0.22
     otherwise
    0.21
     nota
    0.20
     Whether
    0.20
     na
    0.19
    Act Density 0.032%

    No Known Activations