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

    Neuronpedia

    INDEX
    Explanations

    references to identity and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ът
    -0.56
    ︎
    -0.55
     שוליים
    -0.55
     '\\;'
    -0.53
    nloa
    -0.52
    ened
    -0.51
    ThroughAttribute
    -0.51
     CanadaChoose
    -0.50
    ند
    -0.50
    ীয়
    -0.50
    POSITIVE LOGITS
    yyyy
    0.80
    yyy
    0.75
    yyyyy
    0.67
    e
    0.57
    yy
    0.55
    einf
    0.49
    YYYY
    0.49
    깐
    0.48
    eins
    0.47
    ey
    0.46
    Act Density 1.220%

    No Known Activations