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

    Neuronpedia

    INDEX
    Explanations

    words related to negative connotations or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word "rep" indicating repetition or replication in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whitman
    -0.67
     Dragonbound
    -0.65
     Creed
    -0.65
     Dahl
    -0.61
     Glou
    -0.60
     Powell
    -0.60
     Vaughan
    -0.59
     mercury
    -0.59
     Hastings
    -0.59
     Brah
    -0.58
    POSITIVE LOGITS
    ciation
    0.97
    posed
    0.91
    posing
    0.88
    cipled
    0.88
    ciating
    0.84
    lisher
    0.84
    nant
    0.83
    amins
    0.81
    lishing
    0.80
    aration
    0.80
    Act Density 0.062%

    No Known Activations