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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ildo
    -0.15
    onders
    -0.15
    upil
    -0.14
    CHA
    -0.14
    quito
    -0.13
    -animate
    -0.13
    anela
    -0.13
    дап
    -0.13
     Obr
    -0.13
    enties
    -0.13
    POSITIVE LOGITS
     disappointment
    0.78
     disappoint
    0.73
     disappointed
    0.69
     disappointing
    0.63
     disap
    0.43
     antic
    0.29
     expectations
    0.28
     disillusion
    0.28
    whel
    0.27
    whelming
    0.26
    Act Density 0.170%

    No Known Activations