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

    Neuronpedia

    INDEX
    Explanations

    emotional responses or sentiments towards experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hol
    -0.16
    bes
    -0.15
     by
    -0.15
    roker
    -0.15
    374
    -0.15
    ics
    -0.15
    leground
    -0.15
    ↵
    -0.15
    oya
    -0.14
    -0.14
    POSITIVE LOGITS
     having
    0.25
     knowing
    0.23
     hearing
    0.22
    having
    0.22
     seeing
    0.22
     watching
    0.21
     how
    0.18
     Hearing
    0.17
     Having
    0.16
    Having
    0.16
    Act Density 0.194%

    No Known Activations