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

    Neuronpedia

    INDEX
    Explanations

    references to Internet Protocol (IP) addresses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that center around relationships or connections involving "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.77
    ctuary
    -0.75
    idad
    -0.73
    Mex
    -0.70
    Enlarge
    -0.69
    political
    -0.66
    ussen
    -0.65
     whistlebl
    -0.65
    Ô
    -0.64
    Cru
    -0.64
    POSITIVE LOGITS
     each
    0.90
     origin
    0.89
     course
    0.89
     sorts
    0.80
     specified
    0.76
     yours
    0.75
     varying
    0.75
     whichever
    0.74
     corresponding
    0.74
     Origin
    0.73
    Act Density 0.314%

    No Known Activations