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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.76
    “
    -0.73
    yā
    -0.71
    y
    -0.71
    able
    -0.69
    ★★★★★
    -0.67
    <b>
    -0.66
    ctive
    -0.65
    Pare
    -0.65
     Correia
    -0.65
    POSITIVE LOGITS
     M
    1.54
     getM
    1.49
    getM
    1.41
    M
    1.18
     m
    1.10
    pM
    1.07
    iM
    1.04
     М
    1.03
    awtextra
    0.95
    М
    0.95
    Act Density 0.084%

    No Known Activations