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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "In" associated with citations or references in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulan
    -0.16
    resse
    -0.15
    lan
    -0.15
    à¥įरद
    -0.15
    ltra
    -0.14
    uhan
    -0.14
    ndon
    -0.14
    ohn
    -0.14
    жÑĥ
    -0.14
    antar
    -0.14
    POSITIVE LOGITS
    bench
    0.14
    esiz
    0.14
    eps
    0.14
    çį
    0.14
    mobx
    0.14
    _hint
    0.14
    _patterns
    0.14
     unzip
    0.13
    eper
    0.13
    _vertical
    0.13
    Act Density 0.002%

    No Known Activations