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

    Neuronpedia

    INDEX
    Explanations

    words related to specific types of scientific processes or structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation and financial accounting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pool
    -0.77
    fell
    -0.76
    birth
    -0.72
    egg
    -0.70
    Proof
    -0.69
    shirt
    -0.68
    aer
    -0.67
    liness
    -0.66
    hand
    -0.66
    lihood
    -0.66
    POSITIVE LOGITS
    ón
    1.36
    enda
    1.12
    aci
    1.08
    ée
    1.04
    ère
    1.00
    iso
    0.99
    és
    0.93
    opsis
    0.93
    encies
    0.93
    oup
    0.89
    Act Density 0.008%

    No Known Activations