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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing assumptions or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     venons
    -0.73
     Bracken
    -0.69
     allons
    -0.67
     attiv
    -0.66
    ynchro
    -0.64
     Ba
    -0.62
    Milit
    -0.61
    ye
    -0.61
     Werken
    -0.61
    zha
    -0.60
    POSITIVE LOGITS
     assume
    1.55
     Assumptions
    1.48
     assumes
    1.43
    assume
    1.36
     assum
    1.35
     assuming
    1.34
     assumptions
    1.34
     assumed
    1.30
    Assume
    1.28
     Assume
    1.28
    Act Density 0.200%

    No Known Activations