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

    Neuronpedia

    INDEX
    Explanations

    advice or instructions on what to do in various situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases about uncertainty and indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.63
    mot
    -0.61
    members
    -0.59
     Ez
    -0.58
    tun
    -0.58
    bour
    -0.57
    river
    -0.57
    pants
    -0.55
    Mur
    -0.55
    Dur
    -0.55
    POSITIVE LOGITS
     treat
    0.97
     maximize
    0.93
     be
    0.93
     celebrate
    0.90
    ggles
    0.88
     fill
    0.88
     protect
    0.87
     give
    0.87
    iled
    0.87
     take
    0.87
    Act Density 0.080%

    No Known Activations