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

    Neuronpedia

    INDEX
    Explanations

    negative or cautionary statements regarding political or societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political activism and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.84
     Checking
    -0.82
    audio
    -0.79
     suggestive
    -0.78
     researching
    -0.73
    Audio
    -0.73
    76561
    -0.72
     estimating
    -0.70
    checking
    -0.69
     annotations
    -0.69
    POSITIVE LOGITS
     perish
    1.55
     crumble
    1.44
     capit
    1.41
     revolt
    1.37
     starve
    1.36
     prevail
    1.33
     prosper
    1.33
     die
    1.32
     disband
    1.31
     succumb
    1.30
    Act Density 0.330%

    No Known Activations