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

    Neuronpedia

    INDEX
    Explanations

    quantities or comparisons between quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that compare quantities or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.66
    osit
    -0.62
     Firm
    -0.61
    Site
    -0.60
    itiz
    -0.59
    ona
    -0.58
    asta
    -0.57
    asia
    -0.55
    details
    -0.51
     CI
    -0.51
    POSITIVE LOGITS
     barg
    1.09
     ever
    0.88
     otherwise
    0.79
     admit
    0.78
     anticipated
    0.78
    ":[
    0.77
     hitherto
    0.76
     realizes
    0.76
     realize
    0.74
     originally
    0.74
    Act Density 0.151%

    No Known Activations