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

    Neuronpedia

    INDEX
    Explanations

    phrases and discussions related to means and methods of achieving various ends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bing
    -0.17
    gram
    -0.16
    ging
    -0.15
     Harness
    -0.14
    .MouseDown
    -0.14
    jug
    -0.14
    bed
    -0.14
    untime
    -0.14
    ening
    -0.13
    uentes
    -0.13
    POSITIVE LOGITS
    illas
    0.16
    æ¯
    0.15
    Sau
    0.15
    ums
    0.15
    ardi
    0.15
    orial
    0.15
    ioned
    0.15
    ories
    0.15
    SGlobal
    0.14
    lems
    0.14
    Act Density 0.025%

    No Known Activations