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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, such as names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "Te."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     containment
    -0.70
    etheless
    -0.69
    ĸļ
    -0.68
     footing
    -0.63
    iewicz
    -0.62
     Jenner
    -0.61
     ESA
    -0.61
     Throne
    -0.61
    lessly
    -0.61
     totality
    -0.61
    POSITIVE LOGITS
    achable
    1.36
    levision
    1.32
    aching
    1.31
    achers
    1.27
    acher
    1.24
    lev
    1.20
    brate
    1.12
    legram
    1.09
    legraph
    1.07
    ppo
    1.05
    Act Density 0.018%

    No Known Activations