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

    Neuronpedia

    INDEX
    Explanations

    references to the physical top of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the top and bottom positions of objects or items in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.71
    ewitness
    -0.69
    ensable
    -0.68
    accompan
    -0.68
    issance
    -0.65
    OUP
    -0.64
    Corp
    -0.64
    rosso
    -0.63
    emonic
    -0.63
    rought
    -0.63
    POSITIVE LOGITS
     thereof
    1.04
    most
    1.04
     layer
    0.88
     shaft
    0.87
     diameter
    0.84
    pring
    0.83
    portion
    0.82
     portion
    0.82
     lobe
    0.80
     lid
    0.79
    Act Density 0.108%

    No Known Activations