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

    Neuronpedia

    INDEX
    Explanations

    texts referring to various algorithms

    oai_token-act-pair · gpt-3.5-turbo

    references to algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shirt
    -0.73
    joy
    -0.73
    hold
    -0.70
    irts
    -0.69
     Stories
    -0.68
     Pel
    -0.68
    nen
    -0.67
    ership
    -0.66
    holders
    -0.65
    igi
    -0.65
    POSITIVE LOGITS
     algorithms
    1.17
     algorithm
    1.06
    ically
    1.00
    gorithm
    0.94
     optimization
    0.87
    matically
    0.80
    agically
    0.79
    gorith
    0.77
    andom
    0.77
    gebra
    0.74
    Act Density 0.015%

    No Known Activations