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

    Neuronpedia

    INDEX
    Explanations

    strings that start with specific punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    topics related to violence and crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owered
    -0.80
     impacted
    -0.63
    aca
    -0.60
    dict
    -0.58
     enraged
    -0.58
    cedented
    -0.58
    dit
    -0.57
    yp
    -0.57
     rattled
    -0.57
     affected
    -0.56
    POSITIVE LOGITS
     there
    1.45
    there
    1.27
     THERE
    1.18
     There
    1.15
    There
    1.08
     plenty
    0.73
    ossibility
    0.71
     Lots
    0.71
     therein
    0.67
     exists
    0.67
    Act Density 0.355%

    No Known Activations