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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reactions or feedback

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of the term "response" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rome
    -0.84
    cutting
    -0.75
    ramer
    -0.72
    ffe
    -0.67
    teenth
    -0.67
    oak
    -0.66
    cin
    -0.65
     knots
    -0.64
    hemat
    -0.64
    rip
    -0.63
    POSITIVE LOGITS
     thereto
    0.95
     response
    0.90
     responses
    0.81
    ivated
    0.79
     reaction
    0.78
    ively
    0.77
    naires
    0.77
    ivation
    0.74
     elic
    0.74
    aries
    0.72
    Act Density 0.032%

    No Known Activations