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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating undermining or weakening something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that undermine authority or credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ————
    -0.79
    saw
    -0.68
    replace
    -0.67
     followed
    -0.67
    gat
    -0.66
     differs
    -0.65
     avoids
    -0.63
    bg
    -0.63
    tackle
    -0.62
    aido
    -0.62
    POSITIVE LOGITS
     entirety
    1.29
     entire
    1.17
     seriousness
    1.15
     effectiveness
    1.13
     possibility
    1.12
     notion
    1.12
     usefulness
    1.07
     ability
    1.06
     validity
    1.05
     credibility
    1.04
    Act Density 0.265%

    No Known Activations