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

    Neuronpedia

    INDEX
    Explanations

    numbers that are at the beginning of the sentences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to voting or election statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pper
    -0.75
    ipal
    -0.72
    puter
    -0.72
    morning
    -0.71
    atre
    -0.71
    ãĥ£
    -0.71
    alach
    -0.71
    pring
    -0.71
    yright
    -0.70
    plement
    -0.70
    POSITIVE LOGITS
    wcsstore
    0.87
    6666
    0.80
    803
    0.77
    384
    0.76
     ILCS
    0.72
     pounds
    0.69
    EMENT
    0.68
     CLR
    0.68
     Squadron
    0.67
    683
    0.66
    Act Density 0.019%

    No Known Activations