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

    Neuronpedia

    INDEX
    Explanations

    phrases related to correctness and appropriateness in actions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.19
    icap
    -0.18
    ÏģÏĮ
    -0.17
    usz
    -0.17
    ary
    -0.16
    acters
    -0.15
    aries
    -0.15
    оÑĩек
    -0.15
    arine
    -0.15
    że
    -0.14
    POSITIVE LOGITS
    fully
    0.20
     latter
    0.17
    getManager
    0.16
    zem
    0.15
    amt
    0.14
    proper
    0.14
    mente
    0.14
    cast
    0.14
     Proper
    0.14
    adies
    0.14
    Act Density 0.030%

    No Known Activations