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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "seg" and its variants, indicating a focus on segmentation or dividing parts within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etto
    -0.17
    .fx
    -0.16
    xious
    -0.16
    .AutoScaleMode
    -0.15
    erk
    -0.15
     å¾
    -0.15
    ERO
    -0.15
    ório
    -0.14
    zzo
    -0.14
    asive
    -0.14
    POSITIVE LOGITS
    regation
    0.32
    mentation
    0.29
    fault
    0.26
    mented
    0.25
    ments
    0.25
    undo
    0.25
    unda
    0.23
     seg
    0.23
    uridad
    0.23
     Seg
    0.22
    Act Density 0.005%

    No Known Activations