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

    Neuronpedia

    INDEX
    Explanations

    specific instances or scenarios in a given context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "cases" or examples within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.82
    ongyang
    -0.71
    apult
    -0.66
    osponsors
    -0.65
     carbohyd
    -0.63
    ¥ŀ
    -0.62
    ailability
    -0.61
    arching
    -0.61
    arag
    -0.61
     newcom
    -0.61
    POSITIVE LOGITS
    ,
    0.82
    ,,
    0.64
    mma
    0.63
    >>>>>>>>
    0.63
     involving
    0.62
     anyways
    0.61
    forth
    0.61
     anyway
    0.61
    ,.
    0.60
     though
    0.60
    Act Density 0.044%

    No Known Activations