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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with smooth textures or experiences, particularly in relation to drinks or food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áct
    -0.16
    gnore
    -0.15
    idal
    -0.15
    hoe
    -0.15
    htub
    -0.14
    ngr
    -0.14
    auen
    -0.14
    sembled
    -0.14
     suất
    -0.14
    /about
    -0.14
    POSITIVE LOGITS
    est
    0.35
    ness
    0.35
    ie
    0.32
    ies
    0.30
     sailing
    0.27
    s
    0.26
    -running
    0.24
     operator
    0.23
     transitions
    0.23
    -flow
    0.23
    Act Density 0.019%

    No Known Activations