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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting contrast or exception

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and clauses that introduce qualifications or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enced
    -0.65
     Heller
    -0.59
     Yuan
    -0.57
     encyclopedia
    -0.56
     Kaplan
    -0.55
     Turk
    -0.54
     Hat
    -0.53
     atten
    -0.52
     Lam
    -0.51
     Sund
    -0.51
    POSITIVE LOGITS
     guiActiveUn
    0.84
    pton
    0.79
    vc
    0.74
    soever
    0.74
    FW
    0.71
    tan
    0.70
    EVA
    0.70
    unders
    0.68
    TPPStreamerBot
    0.67
    iton
    0.66
    Act Density 0.469%

    No Known Activations