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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thoughts or mental processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "head" or thoughts contained within one's mind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.81
    PsyNetMessage
    -0.75
     Suc
    -0.73
    Constructed
    -0.69
     Vict
    -0.69
     Sparkle
    -0.68
     mell
    -0.65
     Strat
    -0.63
     Virgin
    -0.62
     Danger
    -0.61
    POSITIVE LOGITS
    canon
    1.19
    butt
    1.09
    quarter
    1.08
    scar
    1.06
    gear
    1.03
    dress
    1.01
    shots
    1.00
    liners
    1.00
    lining
    0.99
    phones
    0.99
    Act Density 0.023%

    No Known Activations