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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "be" and forms of the verb "to be" across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ten
    -0.21
     eleven
    -0.17
     tenth
    -0.17
     thousands
    -0.17
     eighth
    -0.16
    Hundreds
    -0.15
    inth
    -0.15
     millions
    -0.15
     ninth
    -0.15
     twelve
    -0.15
    POSITIVE LOGITS
    50
    0.69
    60
    0.69
    65
    0.67
    55
    0.65
    70
    0.64
    52
    0.63
    62
    0.62
    56
    0.62
    54
    0.61
    40
    0.61
    Act Density 0.450%

    No Known Activations