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

    Neuronpedia

    INDEX
    Explanations

    references to software patches and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to software updates or patches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obser
    -0.72
    ¢
    -0.71
    agy
    -0.69
    minist
    -0.69
    yss
    -0.67
     Galile
    -0.65
    VERTISEMENT
    -0.65
    emouth
    -0.65
     temptation
    -0.64
    asonable
    -0.64
    POSITIVE LOGITS
    work
    0.98
    ioned
    0.98
    ions
    0.94
    notes
    0.87
     patched
    0.85
     Patch
    0.84
     patch
    0.84
     patches
    0.77
    ION
    0.75
    ion
    0.73
    Act Density 0.020%

    No Known Activations