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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or condemnation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rings
    -0.75
    agos
    -0.75
    wings
    -0.70
    °
    -0.67
     rematch
    -0.66
     Replacement
    -0.65
     Pastebin
    -0.65
    iage
    -0.64
    chwitz
    -0.64
    ages
    -0.62
    POSITIVE LOGITS
     efficiently
    1.17
    ilaterally
    1.10
     forcefully
    1.05
     violently
    1.05
     securely
    1.05
    successfully
    1.04
    ationally
    1.03
     verbally
    1.02
     smoothly
    0.99
     legally
    0.97
    Act Density 0.170%

    No Known Activations