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

    Neuronpedia

    INDEX
    Explanations

    words related to acts of disruption or subversion

    oai_token-act-pair · gpt-3.5-turbo

    words and sounds that are similar or contain repeated syllables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.85
     triangle
    -0.72
     inaction
    -0.72
     Metatron
    -0.69
    Ļ½
    -0.69
     heresy
    -0.68
     groundwork
    -0.67
     blasphemy
    -0.66
    EVA
    -0.66
     tert
    -0.66
    POSITIVE LOGITS
    glers
    1.00
    oslav
    0.90
    azines
    0.82
    tty
    0.81
    nos
    0.75
    ify
    0.74
    vous
    0.73
    pps
    0.73
     Picks
    0.72
    kies
    0.72
    Act Density 0.058%

    No Known Activations