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

    Neuronpedia

    INDEX
    Explanations

    specific geometric shapes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λÎŃ
    -0.16
    rowsable
    -0.15
    atte
    -0.14
    ût
    -0.14
     Lew
    -0.14
    esper
    -0.14
    IsRequired
    -0.14
    irit
    -0.14
     Wyatt
    -0.13
     Branch
    -0.13
    POSITIVE LOGITS
    encing
    0.16
    ocop
    0.16
    yi
    0.15
    -shaped
    0.15
    Łèĥ½
    0.15
     shaped
    0.15
    lak
    0.14
    -ob
    0.14
    ollo
    0.14
    Ł
    0.14
    Act Density 0.147%

    No Known Activations