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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to fractions or divisions of larger units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìĬµ
    -0.16
    Ñĥже
    -0.15
    yo
    -0.15
    ewise
    -0.14
    ching
    -0.14
    /fw
    -0.14
    zer
    -0.14
    gen
    -0.14
    umer
    -0.14
    elu
    -0.14
    POSITIVE LOGITS
    afia
    0.16
    ÙĨ
    0.16
    lies
    0.15
    ãĥ¼ãĥĪ
    0.15
    ystal
    0.15
    ystone
    0.15
    äch
    0.15
    bread
    0.15
    ìĦľëĬĶ
    0.14
    indrome
    0.14
    Act Density 0.016%

    No Known Activations