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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names associated with specific locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICODE
    -0.16
    Fr
    -0.14
     çĽ
    -0.14
     Rover
    -0.14
    .bytes
    -0.14
    è²´
    -0.13
    antis
    -0.13
     å¾
    -0.13
    gos
    -0.13
     pers
    -0.13
    POSITIVE LOGITS
     Hundred
    0.16
    aho
    0.16
    elian
    0.15
    0.15
     имÑĥ
    0.15
    ominated
    0.14
     anmeld
    0.14
    ::~
    0.13
    iou
    0.13
     Sist
    0.13
    Act Density 0.415%

    No Known Activations