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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names and titles, particularly related to sports journalism and writing

    oai_token-act-pair · gpt-3.5-turbo

    phrases with repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hift
    -0.71
    omm
    -0.70
    ixel
    -0.68
    paces
    -0.67
    zac
    -0.67
    izzard
    -0.64
    omething
    -0.64
    tery
    -0.61
    ARB
    -0.60
    creen
    -0.60
    POSITIVE LOGITS
    --------------------
    0.80
    =-=-
    0.78
     Prev
    0.76
    =-
    0.75
    -.
    0.74
    =~=~
    0.74
    _-
    0.71
     ---------
    0.71
     denotes
    0.70
    âĸł
    0.69
    Act Density 0.042%

    No Known Activations