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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assumptions or presuppositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     venons
    -0.71
     allons
    -0.67
     Ba
    -0.66
     indipendente
    -0.61
     revés
    -0.61
    fcntl
    -0.60
     attiv
    -0.60
    ๆ
    -0.60
     McAllister
    -0.60
     aient
    -0.59
    POSITIVE LOGITS
     assume
    1.49
     assumes
    1.36
    assume
    1.31
     assuming
    1.27
     Assumptions
    1.26
     assum
    1.23
     assumed
    1.23
    Assume
    1.22
     Assume
    1.20
     assumptions
    1.13
    Act Density 0.047%

    No Known Activations