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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or identities, particularly in a historical or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.57
     seiz
    -0.55
     ende
    -0.52
    é¾įå¥ij士
    -0.51
    erous
    -0.51
    ModLoader
    -0.48
     Pengu
    -0.47
    INAL
    -0.47
     surpr
    -0.46
    ģ«
    -0.45
    POSITIVE LOGITS
    ioch
    0.55
    bley
    0.46
    ocene
    0.44
     IDs
    0.43
     pedals
    0.43
    chat
    0.43
     mt
    0.43
    */(
    0.42
    oak
    0.42
    cil
    0.42
    Act Density 1.264%

    No Known Activations