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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flem
    -0.17
    -FIRST
    -0.15
    toHave
    -0.15
    isay
    -0.14
    ieg
    -0.14
    oice
    -0.14
    вок
    -0.14
    avou
    -0.14
    令
    -0.14
    igor
    -0.14
    POSITIVE LOGITS
     feel
    0.23
     aware
    0.18
     happen
    0.17
     laugh
    0.17
     available
    0.16
    /us
    0.16
    216
    0.16
     appear
    0.15
     gig
    0.15
    feel
    0.15
    Act Density 0.033%

    No Known Activations