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

    Neuronpedia

    INDEX
    Explanations

    capitalized words containing special characters

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to events or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.66
    Reviewer
    -0.62
    ŃĶ
    -0.61
    Ü
    -0.60
     Whats
    -0.58
    sticks
    -0.57
    frog
    -0.56
     contrary
    -0.55
     Panthers
    -0.55
    EStream
    -0.54
    POSITIVE LOGITS
    ividual
    0.97
    urities
    0.77
     haste
    0.70
    raft
    0.68
    lass
    0.66
    ãĤ¨ãĥ«
    0.66
    pport
    0.66
    iever
    0.65
    ocent
    0.65
    iband
    0.65
    Act Density 0.076%

    No Known Activations