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

    Neuronpedia

    INDEX
    Explanations

    political groups, individuals, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to groups, communities, or organizations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.64
    and
    -0.61
    cyclopedia
    -0.59
     Ambrose
    -0.58
     throb
    -0.56
     AND
    -0.53
    verbs
    -0.53
     Bellev
    -0.52
     Helsinki
    -0.52
    ologies
    -0.52
    POSITIVE LOGITS
    depending
    1.33
     depending
    1.28
     thereof
    1.05
     whichever
    1.03
     versa
    0.92
     anywhere
    0.89
    atever
    0.88
     alike
    0.87
     whatsoever
    0.86
     respectively
    0.85
    Act Density 0.487%

    No Known Activations