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

    Neuronpedia

    INDEX
    Explanations

    descriptors of softness related to materials or textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    acro
    -0.16
    redient
    -0.15
    áct
    -0.15
    alta
    -0.15
    AVA
    -0.15
    ymmetric
    -0.15
    hta
    -0.14
    anford
    -0.14
    hazi
    -0.14
    POSITIVE LOGITS
    ening
    0.27
    ened
    0.23
    ness
    0.22
    wares
    0.21
    rey
    0.17
    ens
    0.17
    ies
    0.17
    _HINT
    0.16
    NESS
    0.16
    screen
    0.16
    Act Density 0.019%

    No Known Activations