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

    Neuronpedia

    INDEX
    Explanations

    structures that indicate data format or serialization in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [~,
    -0.15
     gridColumn
    -0.14
    .{
    -0.13
    è¦
    -0.13
    ulfill
    -0.13
    èĪ
    -0.13
    kir
    -0.13
    lech
    -0.13
     {@
    -0.13
    #af
    -0.13
    POSITIVE LOGITS
    success
    0.15
    odos
    0.15
    },{↵
    0.15
    Ñıж
    0.14
     //'
    0.14
     tür
    0.14
    otos
    0.14
    åĽº
    0.14
    rms
    0.14
    },↵
    0.13
    Act Density 0.084%

    No Known Activations