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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical or scientific disciplines that describe processes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.23
    houses
    -0.22
    s
    -0.21
    scape
    -0.21
    tings
    -0.20
    sheets
    -0.20
    edList
    -0.20
    ings
    -0.19
    eat
    -0.19
    ing
    -0.19
    POSITIVE LOGITS
    ALLY
    0.61
    ally
    0.56
    ity
    0.46
    all
    0.33
    amente
    0.32
    ian
    0.31
    ians
    0.30
    idal
    0.30
    ism
    0.28
    alex
    0.28
    Act Density 0.174%

    No Known Activations