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

    Neuronpedia

    INDEX
    Explanations

    positive emotions and expressions of enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.15
    rip
    -0.15
    кÑĥлÑı
    -0.15
     æ±
    -0.14
    owed
    -0.14
    üstü
    -0.14
    riet
    -0.14
    iw
    -0.14
    dum
    -0.14
    cury
    -0.14
    POSITIVE LOGITS
     thrill
    0.16
    nest
    0.15
     hearing
    0.15
    entially
    0.15
    itional
    0.15
    adata
    0.15
    idata
    0.14
    yth
    0.14
    orses
    0.14
    ToOne
    0.14
    Act Density 0.081%

    No Known Activations