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

    Neuronpedia

    INDEX
    Explanations

    references to water and its various forms or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.16
    swire
    -0.15
    sets
    -0.15
    ãĥ©ãĥĥãĤ¯
    -0.15
    aces
    -0.15
    sst
    -0.15
    sy
    -0.15
    sw
    -0.15
    ogra
    -0.15
    sv
    -0.14
    POSITIVE LOGITS
    color
    0.26
    colors
    0.25
    colour
    0.25
    ford
    0.24
    fall
    0.23
    melon
    0.23
    front
    0.22
    falls
    0.22
    park
    0.21
    logged
    0.21
    Act Density 0.021%

    No Known Activations