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

    Neuronpedia

    INDEX
    Explanations

    terms related to hijacking incidents or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.19
    uC
    -0.18
    iyan
    -0.17
    uchos
    -0.17
    oje
    -0.17
    ska
    -0.16
    oil
    -0.16
    u
    -0.15
     conform
    -0.15
    ió
    -0.15
    POSITIVE LOGITS
    à¥įà¤ŀ
    0.27
    ournals
    0.23
    ourn
    0.22
    ection
    0.22
    ee
    0.22
    itsu
    0.21
    ournal
    0.21
    oints
    0.21
    acency
    0.20
    t
    0.20
    Act Density 0.057%

    No Known Activations