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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the act of gathering or figuring things out through observations or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating subjective conclusions or interpretations derived from personal experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lover
    -0.63
     goodbye
    -0.60
     Screw
    -0.60
     understatement
    -0.60
     shame
    -0.59
    bent
    -0.58
     Tight
    -0.58
    adem
    -0.57
    btn
    -0.57
    ospons
    -0.56
    POSITIVE LOGITS
     glean
    1.16
     anecd
    1.07
     heard
    1.06
     hears
    1.02
     gather
    0.99
     hear
    0.98
    heard
    0.97
     gathered
    0.94
     understand
    0.93
     learnt
    0.91
    Act Density 0.081%

    No Known Activations