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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a list of items or elements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of" indicating lists or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berus
    -0.71
    oney
    -0.70
    MpServer
    -0.69
     unfocusedRange
    -0.62
    matter
    -0.61
     disposed
    -0.59
     anytime
    -0.58
    ogly
    -0.57
    hya
    -0.57
     buffet
    -0.56
    POSITIVE LOGITS
     Decay
    0.78
    terness
    0.75
     reasons
    0.70
    arching
    0.68
     whom
    0.64
     those
    0.63
     earliest
    0.62
    sers
    0.61
     my
    0.61
    few
    0.59
    Act Density 0.071%

    No Known Activations