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

    Neuronpedia

    INDEX
    Explanations

    locations and events related to specific times and places

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas, at varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     detectors
    -0.70
    DERR
    -0.68
    STDOUT
    -0.64
     footing
    -0.63
    NetMessage
    -0.63
    sylv
    -0.62
     recip
    -0.62
    natureconservancy
    -0.62
    conom
    -0.62
     Logged
    -0.61
    POSITIVE LOGITS
     huh
    0.89
     etc
    0.82
     LLC
    0.78
    032
    0.77
     please
    0.77
     ISBN
    0.75
     eh
    0.74
     ?)
    0.72
     supra
    0.72
     Jr
    0.70
    Act Density 0.457%

    No Known Activations