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

    Neuronpedia

    INDEX
    Explanations

    terms related to mediation or negotiation

    oai_token-act-pair · gpt-3.5-turbo

    words related to mediation or officiating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elong
    -0.74
    ingen
    -0.71
    marked
    -0.69
    este
    -0.69
    repeat
    -0.69
    sand
    -0.68
    mith
    -0.67
    ockets
    -0.65
    writers
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
    POSITIVE LOGITS
    iate
    1.13
    iates
    0.99
    iating
    0.75
    iated
    0.74
    uations
    0.72
    iation
    0.71
    iations
    0.69
    ously
    0.68
    Äĩ
    0.68
    ople
    0.68
    Act Density 0.014%

    No Known Activations