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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional experiences or sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    feeling of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſche
    -0.59
     виправивши
    -0.58
    ntax
    -0.58
    ſelf
    -0.56
    iſchen
    -0.56
    ðsíða
    -0.55
     erſt
    -0.55
    ſcher
    -0.55
    ambién
    -0.54
     }{@
    -0.54
    POSITIVE LOGITS
     feeling
    1.48
    feeling
    1.32
     Feeling
    1.29
    Feeling
    1.23
     feelings
    1.17
    feelings
    1.08
     FEEL
    1.02
     Feelings
    1.01
     sentimento
    0.94
     Gefühl
    0.90
    Act Density 0.010%

    No Known Activations