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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methods of communication or channels of information sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.16
     Mattis
    -0.16
    inya
    -0.15
    ãĥ©ãĥ¼
    -0.15
    kou
    -0.14
    rowable
    -0.14
    ekl
    -0.14
    byt
    -0.14
    pok
    -0.14
    аниÑĨ
    -0.14
    POSITIVE LOGITS
    /in
    0.17
    fleet
    0.14
     dint
    0.14
    ë¡ľëĬĶ
    0.14
     Oswald
    0.14
    ledik
    0.14
    wald
    0.14
    olic
    0.13
    racuse
    0.13
    751
    0.13
    Act Density 0.022%

    No Known Activations