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

    Neuronpedia

    INDEX
    Explanations

    references to clusters or groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    geries
    -0.65
    enterOuterAlt
    -0.61
    elski
    -0.60
    elif
    -0.59
    πει
    -0.59
     CALL
    -0.58
     call
    -0.57
    CALL
    -0.56
     fusca
    -0.54
    iroz
    -0.54
    POSITIVE LOGITS
     estekak
    0.69
     ProtoMessage
    0.66
    serviceWorker
    0.65
     kasarigan
    0.54
    ⓧ
    0.54
     esternos
    0.54
     ddelweddau
    0.53
    WebVitals
    0.52
     NSCoder
    0.52
    曝
    0.51
    Act Density 0.000%

    No Known Activations