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

    Neuronpedia

    INDEX
    Explanations

    highway names with corresponding numbers

    oai_token-act-pair · gpt-3.5-turbo

    negative prefixes or descriptors associated with roads and highways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scalp
    -0.58
     free
    -0.58
     reign
    -0.58
     bailed
    -0.58
     Columbia
    -0.58
     reload
    -0.55
     nights
    -0.54
     correction
    -0.53
     bur
    -0.53
     whichever
    -0.52
    POSITIVE LOGITS
    acan
    1.04
    annis
    0.94
    aca
    0.90
    é¾įå
    0.82
    olit
    0.80
    uct
    0.80
    heart
    0.80
    umerable
    0.79
    ACA
    0.78
    Glass
    0.75
    Act Density 0.091%

    No Known Activations