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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas and pauses in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.64
    ibles
    -0.64
    ª
    -0.60
    pires
    -0.57
     Isles
    -0.57
    oir
    -0.55
    ãĥīãĥ©
    -0.54
    ¥
    -0.54
    :(
    -0.54
    ,.
    -0.53
    POSITIVE LOGITS
     because
    0.93
     but
    0.88
     although
    0.86
     until
    0.84
    ecause
    0.84
    until
    0.83
    because
    0.83
     whereas
    0.83
     lest
    0.79
     preferring
    0.77
    Act Density 0.252%

    No Known Activations