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

    Neuronpedia

    INDEX
    Explanations

    unusual symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or uncommon symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     KH
    -0.41
    ciplinary
    -0.40
     nutshell
    -0.40
    ©¶æ
    -0.39
     Media
    -0.38
     Garry
    -0.38
     Mell
    -0.38
     fielder
    -0.38
     row
    -0.38
     vill
    -0.38
    POSITIVE LOGITS
    sic
    0.70
    emphasis
    0.64
    their
    0.64
    $$$$
    0.61
    rather
    0.59
    something
    0.58
    ONSORED
    0.58
    instead
    0.57
    meaning
    0.57
    they
    0.57
    Act Density 0.730%

    No Known Activations