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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    patterns of letters or sequences resembling abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mehran
    -0.68
    vous
    -0.66
     whe
    -0.61
     Haram
    -0.60
    =""
    -0.60
    apt
    -0.59
    ifer
    -0.59
    VIDIA
    -0.58
    izu
    -0.58
    opard
    -0.57
    POSITIVE LOGITS
    side
    1.00
    pole
    0.87
    views
    0.85
    builders
    0.84
    view
    0.83
    holders
    0.83
     hopping
    0.80
     divid
    0.77
    iers
    0.75
    door
    0.74
    Act Density 0.226%

    No Known Activations