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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions or negotiations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to negotiations and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drivers
    -0.78
    driver
    -0.73
    avis
    -0.72
    Interstitial
    -0.71
    ophone
    -0.70
    phys
    -0.68
    java
    -0.68
    heres
    -0.66
     Flavoring
    -0.65
     ILCS
    -0.65
    POSITIVE LOGITS
     beforehand
    0.80
     timetable
    0.79
    terday
    0.76
     eyebrows
    0.75
    essim
    0.72
     reckon
    0.72
     targ
    0.70
     expectations
    0.69
     concerning
    0.68
     obs
    0.68
    Act Density 0.315%

    No Known Activations