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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that contain special characters such as 'âĢ' or 'ľ'

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and associated numerical values in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.70
     Cind
    -0.66
    agall
    -0.64
     Antar
    -0.64
     thereto
    -0.63
     Hai
    -0.61
     monog
    -0.58
     Roose
    -0.57
    ?).
    -0.57
     Sov
    -0.55
    POSITIVE LOGITS
     guiName
    0.84
    Ability
    0.69
    earable
    0.67
    wcsstore
    0.67
    Split
    0.66
    iculty
    0.66
    requency
    0.65
    ename
    0.64
    Notice
    0.64
    assador
    0.63
    Act Density 0.189%

    No Known Activations