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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental procedures or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to experimental processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cro
    -0.78
    Words
    -0.73
    die
    -0.72
    Word
    -0.72
    HCR
    -0.71
    olulu
    -0.71
    Lo
    -0.70
    si
    -0.70
    lining
    -0.69
    ma
    -0.69
    POSITIVE LOGITS
    imental
    1.17
     experimental
    1.07
     Experimental
    0.95
     experiments
    0.88
     withd
    0.86
     experiment
    0.84
     laboratory
    0.81
     Prototype
    0.81
    ists
    0.78
     Experiment
    0.77
    Act Density 0.009%

    No Known Activations