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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.15
    HEMA
    -0.15
    isis
    -0.14
    ienes
    -0.14
    aste
    -0.14
    _vlog
    -0.14
     Availability
    -0.13
    .synthetic
    -0.13
    atat
    -0.13
     तम
    -0.13
    POSITIVE LOGITS
     being
    0.26
     becoming
    0.18
    being
    0.18
     Being
    0.17
     innov
    0.16
    erc
    0.15
    bidden
    0.15
    flix
    0.15
    Being
    0.15
     coming
    0.14
    Act Density 0.167%

    No Known Activations