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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation involving sets and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <b>
    -0.83
    <sup>
    -0.76
    logenetic
    -0.75
    —
    -0.70
     cours
    -0.70
    γ
    -0.70
    <i>
    -0.69
    к
    -0.68
     compagn
    -0.68
     Langdon
    -0.68
    POSITIVE LOGITS
    =\"
    1.22
     doubtnut
    1.06
     itſelf
    1.03
    =\{
    0.99
     \{\
    0.98
    (\"
    0.97
    IsContent
    0.95
    \{\
    0.95
     $\{\
    0.95
     myſelf
    0.93
    Act Density 0.424%

    No Known Activations