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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating relational or interactive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzle
    -0.15
    ×ķ
    -0.15
    XT
    -0.14
    pitch
    -0.14
    ben
    -0.14
    shed
    -0.14
    obao
    -0.14
    blur
    -0.14
    .defer
    -0.14
    å¬
    -0.13
    POSITIVE LOGITS
    ož
    0.16
    á»ī
    0.15
    iginal
    0.15
    ãĤ¤ãĤº
    0.15
    achu
    0.15
    avo
    0.15
    alette
    0.14
    ilon
    0.14
    ingleton
    0.14
    bots
    0.14
    Act Density 0.025%

    No Known Activations