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

    Neuronpedia

    INDEX
    Explanations

    medically related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of words or phrases indicating intrigue, complexity, or significant emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''
    -0.66
    ''.
    -0.64
    '."
    -0.62
    .''.
    -0.61
    $.
    -0.59
    %.
    -0.56
    .</
    -0.56
    .[
    -0.55
    ."
    -0.55
    .'
    -0.54
    POSITIVE LOGITS
    entious
    0.68
    osponsors
    0.66
    ingly
    0.64
    canon
    0.63
    aciously
    0.63
     concise
    0.63
    recated
    0.62
    omatic
    0.62
    hematically
    0.61
     conject
    0.61
    Act Density 1.255%

    No Known Activations