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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or considering alternatives

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "whether or not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.81
    nee
    -0.67
    ATS
    -0.63
    BOX
    -0.62
     Hilton
    -0.61
    çĶ°
    -0.61
    aturday
    -0.60
    avier
    -0.60
    ANK
    -0.59
    onica
    -0.58
    POSITIVE LOGITS
    acle
    0.99
    Else
    0.99
    acles
    0.98
     else
    0.93
    nam
    0.88
    chard
    0.78
    chid
    0.75
     possibly
    0.71
     otherwise
    0.69
     maybe
    0.68
    Act Density 0.032%

    No Known Activations