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

    Neuronpedia

    INDEX
    Explanations

    geographical directions and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )((((
    -0.16
    ivec
    -0.16
    BOSE
    -0.15
    -gun
    -0.15
    ива
    -0.15
    коÑĢиÑģÑĤ
    -0.15
    /ip
    -0.14
    _ASSUME
    -0.14
    assel
    -0.14
    اÙĨÛĮا
    -0.14
    POSITIVE LOGITS
    ward
    0.19
    ety
    0.17
    spir
    0.16
    bound
    0.16
    ory
    0.15
     Abrams
    0.15
    uy
    0.15
    urt
    0.14
    ier
    0.14
    wise
    0.14
    Act Density 0.026%

    No Known Activations