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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions related to conflict or controversial situations

    oai_token-act-pair · gpt-3.5-turbo

    references to conflict, medical practices, and associated societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutshell
    -0.67
    [/
    -0.61
    achu
    -0.60
     Announce
    -0.59
    iversary
    -0.56
    ovie
    -0.55
     Anniversary
    -0.54
    laughter
    -0.54
    alion
    -0.54
    STER
    -0.54
    POSITIVE LOGITS
     themselves
    0.90
     theirs
    0.79
     their
    0.74
     elsewhere
    0.73
     costly
    0.68
    their
    0.65
     tailored
    0.64
     lucrative
    0.63
     backgrounds
    0.62
     nearby
    0.62
    Act Density 1.058%

    No Known Activations