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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistical data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.80
     newsp
    -0.71
     plateau
    -0.71
     culminating
    -0.69
    spread
    -0.68
     accelerating
    -0.68
     explos
    -0.67
     heroine
    -0.64
    agine
    -0.63
     manifold
    -0.63
    POSITIVE LOGITS
     ILCS
    1.18
    00
    1.08
    81
    1.07
    70
    1.06
    61
    1.06
    79
    1.05
    84
    1.05
    82
    1.05
    66
    1.05
    87
    1.04
    Act Density 0.143%

    No Known Activations