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

    Neuronpedia

    INDEX
    Explanations

    instances of criticism and its various forms in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĢει
    -0.16
    cribe
    -0.15
    ook
    -0.15
    ause
    -0.14
    ey
    -0.14
     grace
    -0.14
    itre
    -0.14
    ryo
    -0.14
    ent
    -0.14
    ente
    -0.14
    POSITIVE LOGITS
    -minded
    0.18
    icism
    0.17
    atory
    0.17
    atically
    0.17
    izes
    0.16
    imler
    0.16
    kovi
    0.15
     minded
    0.15
    voices
    0.15
    antium
    0.15
    Act Density 0.036%

    No Known Activations