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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of substitution or replacing items or ideas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     препратки
    -0.92
    +#+#
    -0.75
    readAs
    -0.71
    whel
    -0.68
    pla
    -0.66
     Baek
    -0.66
    Odon
    -0.66
    NEC
    -0.65
     GlobalKey
    -0.63
    nextProps
    -0.63
    POSITIVE LOGITS
    0.88
    shed
    0.78
     Salter
    0.77
     Schn
    0.73
     doux
    0.71
    CrossRef
    0.70
     PLWABN
    0.70
     Mustard
    0.70
     FontWeight
    0.69
    WEET
    0.69
    Act Density 0.004%

    No Known Activations