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

    Neuronpedia

    INDEX
    Explanations

    short phrases indicating reading or consuming information

    oai_token-act-pair · gpt-3.5-turbo

    references to full stories or comprehensive reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĺ
    -0.84
    factor
    -0.72
    uca
    -0.71
    Invalid
    -0.68
    Detect
    -0.67
    Factor
    -0.66
    Tier
    -0.66
    #$
    -0.66
    drm
    -0.65
    Frameworks
    -0.65
    POSITIVE LOGITS
     full
    1.38
     entire
    1.19
     rest
    1.18
     latest
    1.16
     entirety
    1.15
     FULL
    1.08
     whole
    1.07
     complete
    1.04
     slideshow
    1.02
     original
    1.02
    Act Density 0.144%

    No Known Activations