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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the outer appearance or surface characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate superficiality or appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rons
    -0.73
    Els
    -0.67
    iband
    -0.66
    rys
    -0.64
    adr
    -0.63
    igers
    -0.63
    iru
    -0.63
    CHQ
    -0.62
    ĸļ
    -0.61
    WR
    -0.61
    POSITIVE LOGITS
     nutshell
    0.88
     glance
    0.73
     standpoint
    0.70
    ij士
    0.69
     hindsight
    0.68
     Appearance
    0.64
    speaking
    0.64
     aside
    0.63
     synopsis
    0.63
     though
    0.61
    Act Density 0.186%

    No Known Activations