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

    Neuronpedia

    INDEX
    Explanations

    references to personal memories or recollections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of remembrance and nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hello
    -0.77
    Bang
    -0.65
     ',
    -0.62
    ðŁĺ
    -0.61
     ['
    -0.61
    )"
    -0.60
     Bang
    -0.58
     Drinking
    -0.58
    Champ
    -0.58
     Illegal
    -0.56
    POSITIVE LOGITS
     nonetheless
    1.07
    etheless
    1.04
     similarly
    0.97
     likewise
    0.94
     conspic
    0.91
     downright
    0.88
     equally
    0.87
     nevertheless
    0.85
     unwittingly
    0.85
     understandably
    0.84
    Act Density 0.917%

    No Known Activations