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

    Neuronpedia

    INDEX
    Explanations

    sentences about scientific or technical content, such as research findings or laboratory procedures

    oai_token-act-pair · gpt-3.5-turbo

    sentences that signify conclusions or end statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estate
    -0.83
    ibur
    -0.82
    iquette
    -0.81
     silent
    -0.76
     buggy
    -0.75
     revol
    -0.74
     dirt
    -0.73
     treasury
    -0.73
     extortion
    -0.73
     mustache
    -0.73
    POSITIVE LOGITS
     Researchers
    1.39
     Scientists
    1.36
     Furthermore
    1.26
     PLoS
    1.25
     Moreover
    1.25
    Researchers
    1.13
    Scientists
    1.11
     Previous
    1.10
     Therefore
    1.09
     Molecular
    1.08
    Act Density 0.331%

    No Known Activations