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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "se" or its attached forms, likely indicating references to division, separation, or individual parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agon
    -0.62
     owl
    -0.61
     UID
    -0.59
     crooked
    -0.59
     McH
    -0.59
     liking
    -0.58
     mock
    -0.57
    STER
    -0.57
     hawk
    -0.56
     Scully
    -0.56
    POSITIVE LOGITS
    eker
    1.03
    mination
    1.01
    gger
    1.00
    vier
    0.92
    rer
    0.91
    vich
    0.91
    ptic
    0.91
    xy
    0.90
    vent
    0.90
    ld
    0.89
    Act Density 0.025%

    No Known Activations