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

    Neuronpedia

    INDEX
    Explanations

    phrases related to teaching, training, or mentoring

    oai_token-act-pair · gpt-3.5-turbo

    elements related to judgment, evaluation, or appraisal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (£
    -0.74
     maths
    -0.66
     flavours
    -0.64
     flavour
    -0.64
     neighbourhood
    -0.62
     £
    -0.62
     Centre
    -0.62
     scept
    -0.62
     programmes
    -0.61
     programme
    -0.61
    POSITIVE LOGITS
    ,,,,
    0.78
    hovah
    0.69
     utilizing
    0.63
     favorably
    0.62
    arger
    0.62
     utilizes
    0.61
    theless
    0.60
     accomplish
    0.58
     thous
    0.58
    ////////////////
    0.57
    Act Density 1.551%

    No Known Activations