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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.78
    ties
    -0.76
    FIELD
    -0.69
    CLASSIFIED
    -0.69
    amphetamine
    -0.68
    zees
    -0.66
    quit
    -0.66
    arrow
    -0.65
    deals
    -0.64
    reditary
    -0.64
    POSITIVE LOGITS
     interviewer
    0.96
     latter
    0.95
     same
    0.92
     BBC
    0.90
     latest
    0.86
     audience
    0.83
     Huffington
    0.83
     contrary
    0.80
     court
    0.79
     Associated
    0.78
    Act Density 0.095%

    No Known Activations