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

    Neuronpedia

    INDEX
    Explanations

    mentions of qualifications or being qualified

    oai_token-act-pair · gpt-3.5-turbo

    references to qualifications or competency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.98
     Sparrow
    -0.78
     DRAG
    -0.71
     Spiegel
    -0.67
     Gardens
    -0.66
     drip
    -0.66
    corn
    -0.66
    âĸ¬âĸ¬
    -0.65
     strand
    -0.65
     Decay
    -0.64
    POSITIVE LOGITS
     qualifications
    0.93
    dinand
    0.87
    ifiers
    0.86
    ifications
    0.86
    ifies
    0.85
    ified
    0.83
    animous
    0.83
    ifying
    0.82
    ategor
    0.82
    itably
    0.82
    Act Density 0.015%

    No Known Activations