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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing textures or consistencies

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajor
    -0.77
    href
    -0.73
    roit
    -0.72
    uther
    -0.71
    itutional
    -0.71
     Examiner
    -0.70
    rait
    -0.68
    channelAvailability
    -0.67
    podcast
    -0.65
    ainer
    -0.65
    POSITIVE LOGITS
     eyed
    0.97
    ness
    0.96
    bean
    0.80
    glers
    0.78
     sounding
    0.77
    nesses
    0.75
     enough
    0.74
     greens
    0.74
    balls
    0.73
     tendencies
    0.73
    Act Density 0.056%

    No Known Activations