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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or characters starting with "Kee", "Flan", "Moor", or "Lime"

    oai_token-act-pair · gpt-3.5-turbo

    proper names and specific key terms related to individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atted
    -0.74
    ERAL
    -0.73
    ainer
    -0.73
    ails
    -0.69
    iaries
    -0.68
    icates
    -0.67
    ivals
    -0.67
    umped
    -0.66
    icating
    -0.65
    ications
    -0.64
    POSITIVE LOGITS
    ppo
    1.23
    lette
    0.93
    gas
    0.90
    ppe
    0.87
    bley
    0.84
    lling
    0.84
    ffe
    0.81
    vine
    0.81
    xus
    0.80
    nery
    0.79
    Act Density 0.045%

    No Known Activations