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

    Neuronpedia

    INDEX
    Explanations

    words related to correctness and properness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.20
    ÏģÏĮ
    -0.17
    icap
    -0.16
    arine
    -0.15
    usz
    -0.15
    aries
    -0.15
    éli
    -0.14
    ary
    -0.14
    że
    -0.14
    оÑĩек
    -0.14
    POSITIVE LOGITS
    fully
    0.20
     latter
    0.16
    erken
    0.15
     Proper
    0.15
    proper
    0.15
    ìĿ´ê³ł
    0.14
    izont
    0.14
    edList
    0.14
    ately
    0.14
    dess
    0.14
    Act Density 0.030%

    No Known Activations