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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions and feelings expressed in literary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    u
    -0.44
    at
    -0.35
    ar
    -0.33
    w
    -0.33
    on
    -0.32
    f
    -0.29
    ÙĪ
    -0.29
    k
    -0.28
    l
    -0.28
    id
    -0.28
    POSITIVE LOGITS
    eel
    0.21
    æĺ¯æĪij
    0.18
    edor
    0.16
    ity
    0.16
     otherwise
    0.16
    eriod
    0.15
    neau
    0.15
    erin
    0.15
    oise
    0.15
     OTHERWISE
    0.15
    Act Density 0.549%

    No Known Activations