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

    Neuronpedia

    INDEX
    Explanations

    concepts related to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tigs
    -0.37
     novel
    -0.34
     acta
    -0.33
     passé
    -0.32
     passée
    -0.32
    ğlık
    -0.31
     tack
    -0.30
    dom
    -0.30
     curio
    -0.30
     novels
    -0.30
    POSITIVE LOGITS
     knows
    0.82
    Knows
    0.78
    knows
    0.77
    knowing
    0.76
    OGND
    0.75
     knew
    0.75
     Knows
    0.74
     conscientes
    0.73
     ProtoMessage
    0.72
     understands
    0.72
    Act Density 0.360%

    No Known Activations