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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of doing something for a specific purpose or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spell
    -0.16
    egen
    -0.16
     ÑĪÑĤ
    -0.15
    à¸ģ
    -0.15
    URLRequest
    -0.15
    apl
    -0.15
    arth
    -0.15
    aro
    -0.14
    vida
    -0.14
    åĨł
    -0.14
    POSITIVE LOGITS
    hod
    0.16
     substant
    0.14
    tres
    0.14
    elog
    0.14
    orney
    0.14
     taj
    0.14
     alone
    0.14
    _compat
    0.14
     Luna
    0.14
    оÑĩ
    0.13
    Act Density 0.003%

    No Known Activations