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

    Neuronpedia

    INDEX
    Explanations

    instances of significant verbs or actions in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bonnie
    -0.17
    游
    -0.15
    .Loader
    -0.15
    edir
    -0.15
    ogle
    -0.14
    ounge
    -0.14
    itra
    -0.14
    ÑĢоп
    -0.14
    unya
    -0.14
    BufferSize
    -0.14
    POSITIVE LOGITS
    nell
    0.15
     gross
    0.15
    hus
    0.15
    æ¡
    0.15
    alara
    0.14
    alink
    0.14
    nel
    0.14
    ANCH
    0.13
    isis
    0.13
    nels
    0.13
    Act Density 0.002%

    No Known Activations