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

    Neuronpedia

    INDEX
    Explanations

    expressions related to work or employment

    oai_token-act-pair · gpt-3.5-turbo

    themes related to love, denial, and philosophical inquiries about human existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.65
    ticket
    -0.63
    OPS
    -0.63
    eligible
    -0.63
    çīĪ
    -0.60
    ouri
    -0.59
    CDC
    -0.59
    vertisement
    -0.58
    Department
    -0.58
    leased
    -0.58
    POSITIVE LOGITS
     consciousness
    1.09
     emotions
    1.05
     transcend
    1.03
     individuality
    1.02
     spirituality
    1.02
     innate
    0.99
     emotion
    0.99
     intellect
    0.98
     pleasures
    0.97
     sexuality
    0.95
    Act Density 0.873%

    No Known Activations