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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requires
    -0.80
    interstitial
    -0.76
    urable
    -0.69
    pie
    -0.67
    hent
    -0.66
    quet
    -0.65
    washer
    -0.63
    named
    -0.62
    advertising
    -0.61
    posted
    -0.61
    POSITIVE LOGITS
     settle
    1.19
     spare
    1.18
     explore
    1.17
     negotiate
    1.14
     prepare
    1.13
     consolidate
    1.10
     develop
    1.09
     accumulate
    1.09
     comply
    1.07
     recover
    1.07
    Act Density 0.072%

    No Known Activations