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

    Neuronpedia

    INDEX
    Explanations

    words related to predictions and assumptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.68
    dylib
    -0.66
     Monitor
    -0.66
    ebted
    -0.65
    ologue
    -0.63
     Reporting
    -0.61
    Gallery
    -0.60
     Ow
    -0.60
     watches
    -0.60
     Tables
    -0.59
    POSITIVE LOGITS
     counterproductive
    1.14
     fraught
    1.12
     preferable
    1.07
     frowned
    1.02
     futile
    1.02
     taboo
    1.01
     advisable
    1.00
     paramount
    0.97
     pointless
    0.97
     folly
    0.96
    Act Density 1.543%

    No Known Activations