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

    Neuronpedia

    INDEX
    Explanations

    references to technology or software modules

    oai_token-act-pair · gpt-3.5-turbo

    references to software modules and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guan
    -0.73
    photo
    -0.71
    creen
    -0.71
    vo
    -0.70
    ews
    -0.70
    furt
    -0.70
    isconsin
    -0.69
     Lauder
    -0.66
    ãĥī
    -0.66
    bow
    -0.66
    POSITIVE LOGITS
     loader
    0.92
     modules
    0.89
     bund
    0.86
    modules
    0.86
    ules
    0.84
    mers
    0.78
    matically
    0.74
     vit
    0.72
     imports
    0.70
    orrow
    0.69
    Act Density 0.022%

    No Known Activations