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

    Neuronpedia

    INDEX
    Explanations

    the contraction "I've" preceding different activities or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experience or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odder
    -0.71
    alyses
    -0.70
    winner
    -0.64
     Shots
    -0.62
     Crus
    -0.62
    Subject
    -0.62
    orage
    -0.60
     Skydragon
    -0.60
    osion
    -0.59
    ologically
    -0.59
    POSITIVE LOGITS
     been
    1.20
    been
    1.12
     Been
    1.06
    theless
    0.90
    gotten
    0.90
     gotten
    0.84
    tta
    0.84
     got
    0.83
     learnt
    0.80
     gotta
    0.80
    Act Density 0.029%

    No Known Activations