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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions or specifications

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footing
    -0.61
    ocl
    -0.60
     convictions
    -0.60
    odes
    -0.60
     experience
    -0.57
     inquiry
    -0.56
     reasons
    -0.55
    enhagen
    -0.55
     instincts
    -0.55
    ogeneity
    -0.54
    POSITIVE LOGITS
     aka
    1.06
     which
    1.01
     respectively
    0.97
     whereas
    0.93
     although
    0.93
     wherein
    0.90
    Downloadha
    0.90
     etc
    0.89
     meanwhile
    0.84
    which
    0.83
    Act Density 0.847%

    No Known Activations