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

    Neuronpedia

    INDEX
    Explanations

    the word "still" indicating a sense of continuity or permanence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »¿
    -2.75
    ¯
    -2.69
    ģ
    -2.66
    ĨĴ
    -2.65
    ĥ½
    -2.57
    ĵ
    -2.50
    ij
    -2.45
    Ģ
    -2.41
    Ķ
    -2.38
    Ĵ
    -2.33
    POSITIVE LOGITS
    ilage
    1.71
    stock
    1.71
    sti
    1.67
    birth
    1.57
    ération
    1.56
    ylvania
    1.54
    jam
    1.53
    reaction
    1.49
    capacity
    1.49
    iosis
    1.47
    Act Density 0.060%

    No Known Activations