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

    Neuronpedia

    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and structure related to formal writing or reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teleport
    -0.81
     glide
    -0.77
     regenerate
    -0.75
     finishing
    -0.75
     finish
    -0.72
     abandon
    -0.72
     tempo
    -0.71
     electr
    -0.69
     plunge
    -0.69
     ability
    -0.69
    POSITIVE LOGITS
    SPONSORED
    1.21
    Anonymous
    1.20
    According
    1.15
    ccording
    1.15
    However
    1.09
    Published
    1.09
    Yesterday
    1.07
    Specifically
    1.05
    Comment
    1.03
    Statement
    1.03
    Act Density 0.841%

    No Known Activations