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

    Neuronpedia

    INDEX
    Explanations

    words that indicate existence and presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apel
    -0.15
    AIL
    -0.15
    биÑĤ
    -0.15
    nek
    -0.14
    AA
    -0.14
    adas
    -0.13
    .generated
    -0.13
     Private
    -0.13
    erg
    -0.13
    illary
    -0.13
    POSITIVE LOGITS
    üst
    0.15
    isman
    0.15
    ijo
    0.15
    posix
    0.15
    grounds
    0.15
    çĩĥ
    0.14
    aket
    0.14
    ijk
    0.14
    istant
    0.14
    layan
    0.14
    Act Density 0.000%

    No Known Activations