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

    Neuronpedia

    INDEX
    Explanations

    topics related to broadcast, entertainment industry, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to media, legal issues, and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.68
    )=(
    -0.66
    ometimes
    -0.65
    gypt
    -0.65
    rongh
    -0.64
    pherd
    -0.63
    ortment
    -0.60
    LM
    -0.59
    adder
    -0.59
    prem
    -0.58
    POSITIVE LOGITS
     whatsoever
    1.62
     nor
    1.22
     anymore
    0.98
     except
    0.87
     anywhere
    0.74
     affiliation
    0.73
     describ
    0.72
     markings
    0.71
     slightest
    0.71
     anybody
    0.70
    Act Density 0.201%

    No Known Activations