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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.50
     butt
    -0.49
    IVENESS
    -0.47
     celu
    -0.47
    kologi
    -0.47
    ValueStyle
    -0.46
    ulose
    -0.46
    getDoctrine
    -0.45
    ogaster
    -0.44
    Билгалдахарш
    -0.44
    POSITIVE LOGITS
     pourtant
    0.82
     ellers
    0.72
     betrayal
    0.64
     autrefois
    0.61
     inoxidable
    0.61
     inoxid
    0.61
     betrayed
    0.60
     Pourtant
    0.59
     disappointing
    0.57
     trusted
    0.56
    Act Density 0.240%

    No Known Activations