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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and sensory words related to temperature, health, and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessness
    -0.21
    raq
    -0.19
    thing
    -0.17
    naments
    -0.16
    eum
    -0.16
    eru
    -0.15
    orgia
    -0.15
    ocks
    -0.15
    osal
    -0.14
    ods
    -0.14
    POSITIVE LOGITS
     enough
    0.33
    ly
    0.26
    (er
    0.23
     Enough
    0.22
    ish
    0.22
     AF
    0.21
    ened
    0.20
    -looking
    0.20
    ness
    0.20
    Enough
    0.18
    Act Density 0.435%

    No Known Activations