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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quotes or attributed speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©
    -0.16
    вий
    -0.15
    æŀ
    -0.14
     Treasure
    -0.14
    reno
    -0.14
    kses
    -0.14
     said
    -0.13
    _sched
    -0.13
    /--
    -0.13
    dda
    -0.13
    POSITIVE LOGITS
     explains
    0.28
     says
    0.21
     explain
    0.18
     Says
    0.18
    explain
    0.16
     explaining
    0.16
    _UNIFORM
    0.16
     describes
    0.15
     notes
    0.15
    772
    0.15
    Act Density 0.101%

    No Known Activations