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

    Neuronpedia

    INDEX
    Explanations

    phrases related to issues of conflict or contention

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenges or issues in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rampage
    -0.65
    Medium
    -0.57
    illard
    -0.55
    ŃĶ
    -0.55
    etheless
    -0.54
    Shares
    -0.54
    amina
    -0.54
    arez
    -0.53
    WARD
    -0.53
    rose
    -0.53
    POSITIVE LOGITS
     accountable
    0.63
     squarely
    0.60
    sers
    0.60
     shine
    0.60
     away
    0.59
    ibel
    0.58
     iP
    0.58
     Pagan
    0.58
     aside
    0.57
     Pry
    0.56
    Act Density 0.625%

    No Known Activations