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

    Neuronpedia

    INDEX
    Explanations

    phrases describing alignment or positioning

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "lined up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KEN
    -0.72
     Mansion
    -0.63
    tymology
    -0.58
     cac
    -0.57
    aken
    -0.56
    orem
    -0.56
    matter
    -0.56
     Whitman
    -0.56
    fulness
    -0.56
    obi
    -0.55
    POSITIVE LOGITS
    river
    0.81
    etter
    0.73
    inar
    0.69
    stairs
    0.68
    isexual
    0.66
    uce
    0.65
    Border
    0.64
    dates
    0.64
    tics
    0.64
    eret
    0.64
    Act Density 0.040%

    No Known Activations