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

    Neuronpedia

    INDEX
    Explanations

    mentions of technical details related to software and systems

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating failures or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.62
     himself
    -0.60
     Flavoring
    -0.58
    pires
    -0.57
    \\\\\\\\
    -0.55
     awaits
    -0.54
    issance
    -0.54
     presiding
    -0.53
     retains
    -0.52
     believes
    -0.52
    POSITIVE LOGITS
     expire
    0.75
     themselves
    0.74
    geries
    0.70
    were
    0.68
     spaced
    0.66
     vary
    0.66
    ensitive
    0.63
     differ
    0.62
     uniformly
    0.61
     individually
    0.60
    Act Density 1.172%

    No Known Activations