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

    Neuronpedia

    INDEX
    Explanations

    names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated letters or sounds in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.67
    ĪĴ
    -0.66
     epid
    -0.63
    imeters
    -0.62
    lessly
    -0.60
    ught
    -0.60
     coffin
    -0.59
    minist
    -0.58
    ModLoader
    -0.58
    istry
    -0.57
    POSITIVE LOGITS
    zyk
    1.02
    owicz
    0.79
    osaurus
    0.76
    amins
    0.75
    elson
    0.75
    bos
    0.72
    opol
    0.72
    Roberts
    0.72
    ée
    0.72
     Sabha
    0.71
    Act Density 0.232%

    No Known Activations