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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONEY
    -0.82
    çİĭ
    -0.78
    GBT
    -0.74
    opian
    -0.70
    comfort
    -0.70
    ANY
    -0.69
    oldemort
    -0.67
    yip
    -0.66
    DERR
    -0.66
    PATH
    -0.65
    POSITIVE LOGITS
    pires
    0.78
     nutshell
    0.75
     Lun
    0.65
     Rev
    0.62
     Squirrel
    0.62
     Iv
    0.62
     Aging
    0.62
     Action
    0.62
     Movies
    0.61
     Decay
    0.61
    Act Density 0.746%

    No Known Activations