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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express relationships or references to ownership and possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efully
    -0.67
    Ire
    -0.65
    jri
    -0.65
     advoc
    -0.64
     destro
    -0.63
    wcs
    -0.63
     Vaugh
    -0.61
     accordingly
    -0.61
    DAQ
    -0.59
    aturdays
    -0.59
    POSITIVE LOGITS
     largeDownload
    0.67
     âĵĺ
    0.61
    ¶
    0.56
     invention
    0.55
     Aviation
    0.55
     Abandon
    0.55
     FIG
    0.53
     Artificial
    0.53
     Mars
    0.52
     nutshell
    0.50
    Act Density 0.383%

    No Known Activations