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

    Neuronpedia

    INDEX
    Explanations

    unfamiliar symbols and formatting patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or controversial events involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.88
     revolving
    -0.76
     Clicker
    -0.74
     tremend
    -0.74
    omorphic
    -0.73
     eleph
    -0.72
     referen
    -0.72
     veter
    -0.70
     obser
    -0.69
    rolet
    -0.69
    POSITIVE LOGITS
    Washington
    0.93
    Adds
    0.82
    Experts
    0.79
    Officials
    0.78
    Authorities
    0.77
    Government
    0.75
    They
    0.75
    Scientists
    0.73
    they
    0.73
    Critics
    0.70
    Act Density 0.057%

    No Known Activations