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

    Neuronpedia

    INDEX
    Explanations

    references to lip movements or lip service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leap
    -0.84
    ISION
    -0.83
    IRD
    -0.75
     Samar
    -0.68
    theless
    -0.67
     Blessed
    -0.67
    ENCY
    -0.66
    NESS
    -0.66
     ESV
    -0.65
     Reloaded
    -0.65
    POSITIVE LOGITS
    sticks
    1.06
    atures
    0.98
    stick
    0.97
    ograph
    0.95
    ids
    0.94
    ogenesis
    0.94
    seys
    0.93
    ogen
    0.91
    etsk
    0.90
    ograms
    0.89
    Act Density 0.008%

    No Known Activations