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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hani
    -0.16
    anja
    -0.15
    ï¼³
    -0.14
    ATRIX
    -0.14
    ãģŁãģĹ
    -0.14
    há
    -0.14
    ï¼´
    -0.14
    Å¡ak
    -0.14
    _bitmap
    -0.13
    REP
    -0.13
    POSITIVE LOGITS
    edis
    0.16
    et
    0.15
    ieder
    0.15
    å±ħ
    0.15
    igger
    0.15
    edin
    0.15
    uela
    0.15
     tal
    0.14
    gan
    0.14
     Tal
    0.14
    Act Density 0.236%

    No Known Activations