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

    Neuronpedia

    INDEX
    Explanations

    terms related to speculation and assessments about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anas
    -0.15
    lord
    -0.15
    oms
    -0.15
    InstanceId
    -0.15
    ész
    -0.15
    ances
    -0.14
    olen
    -0.14
    éĻ¢
    -0.14
    osten
    -0.14
    mand
    -0.14
    POSITIVE LOGITS
    imen
    0.18
    zi
    0.17
    nish
    0.17
    ulative
    0.17
    ifo
    0.17
    ãĥ¼ãĥĦ
    0.17
    izoph
    0.17
    ple
    0.17
    uzz
    0.16
    imens
    0.16
    Act Density 0.067%

    No Known Activations