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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting or referencing written communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Charter
    -0.15
    ore
    -0.14
    vert
    -0.14
    kus
    -0.14
     Pes
    -0.14
    bro
    -0.14
    -only
    -0.14
     McA
    -0.14
    boarding
    -0.13
    omor
    -0.13
    POSITIVE LOGITS
    ç¿Ķ
    0.18
    ROY
    0.16
    flix
    0.15
    irected
    0.14
    rene
    0.14
    itech
    0.14
    (Container
    0.14
    ì³
    0.14
     betr
    0.14
    ãĥŁãĥ¥
    0.14
    Act Density 0.017%

    No Known Activations