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

    Neuronpedia

    INDEX
    Explanations

    numbered lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly related to data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     credential
    -0.60
    acre
    -0.57
    76561
    -0.57
     convict
    -0.55
     unfl
    -0.54
     wrench
    -0.54
     descript
    -0.53
     imag
    -0.52
     env
    -0.50
     aroused
    -0.50
    POSITIVE LOGITS
    iard
    0.68
     Pharaoh
    0.65
     Lastly
    0.64
    aints
    0.64
    amins
    0.63
     Puzzles
    0.62
    eor
    0.58
     Conclusion
    0.57
    ulhu
    0.57
     targ
    0.57
    Act Density 0.079%

    No Known Activations