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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "each" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klo
    -0.74
     Bons
    -0.67
     Cof
    -0.66
    buster
    -0.66
     Goy
    -0.65
    Klo
    -0.64
     Cune
    -0.64
     Humphries
    -0.63
     SUT
    -0.62
     FMI
    -0.60
    POSITIVE LOGITS
    EACH
    1.44
     EACH
    1.37
     each
    1.26
    each
    1.25
     Each
    1.20
    Each
    1.19
    각
    1.12
    masing
    1.09
    BeforeEach
    1.03
    ReusableCell
    1.02
    Act Density 0.066%

    No Known Activations