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

    Neuronpedia

    INDEX
    Explanations

    text formats and file-related terms

    oai_token-act-pair · gpt-3.5-turbo

    technical and data-related terms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.82
    urat
    -0.73
    itness
    -0.73
    earchers
    -0.71
    ichever
    -0.70
     answ
    -0.70
    iologist
    -0.68
    eus
    -0.68
    icipated
    -0.67
    iversary
    -0.67
    POSITIVE LOGITS
     Paste
    0.82
    ...]
    0.75
    rawdownloadcloneembedreportprint
    0.73
     LOG
    0.69
     Lod
    0.69
     Suff
    0.65
    ][/
    0.65
    ]:
    0.64
    Ĥª
    0.64
     ]
    0.63
    Act Density 0.060%

    No Known Activations