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

    Neuronpedia

    INDEX
    Explanations

    phrases describing characteristics or actions related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases focusing on individuals and their characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tes
    -0.70
    MSN
    -0.65
    mx
    -0.62
     Panic
    -0.62
    Drag
    -0.62
     Fusion
    -0.61
     Briggs
    -0.60
     Corpus
    -0.60
    ICE
    -0.59
     Mig
    -0.58
    POSITIVE LOGITS
     consequently
    0.88
     furthermore
    0.84
     thereby
    0.84
    etheless
    0.81
     nevertheless
    0.76
     thereafter
    0.75
     conclud
    0.75
     therefore
    0.74
     secondly
    0.73
    anwhile
    0.72
    Act Density 0.674%

    No Known Activations