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

    Neuronpedia

    INDEX
    Explanations

    unintelligible or garbled text

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nationals
    -0.55
     Forums
    -0.53
     Gazette
    -0.50
     Tours
    -0.50
     Lynn
    -0.49
     unanimously
    -0.49
     Drag
    -0.48
     toured
    -0.47
     signs
    -0.47
     Santiago
    -0.47
    POSITIVE LOGITS
    matical
    0.73
    itu
    0.68
    edo
    0.66
    vious
    0.65
    plet
    0.65
    dden
    0.64
    matic
    0.63
    erous
    0.63
    igible
    0.62
    cious
    0.62
    Act Density 0.631%

    No Known Activations