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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distances and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating urgency or prompt action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anium
    -0.70
    dimension
    -0.68
    soDeliveryDate
    -0.68
    oshenko
    -0.68
    atom
    -0.65
     historically
    -0.65
     inherit
    -0.64
    agine
    -0.64
    cancer
    -0.64
    mite
    -0.63
    POSITIVE LOGITS
     proceeded
    0.91
     calmed
    0.89
     relent
    0.86
     promptly
    0.85
     reluctantly
    0.85
     quickly
    0.84
     applause
    0.82
     hurried
    0.81
     reply
    0.80
     calmly
    0.79
    Act Density 1.150%

    No Known Activations