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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attentiveness or eagerness

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases indicating attentiveness or sensitivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISA
    -0.76
    UC
    -0.74
     guiActiveUn
    -0.69
    ulia
    -0.69
    emetery
    -0.67
    DragonMagazine
    -0.65
    ESA
    -0.64
    stanbul
    -0.64
    MU
    -0.62
     ceiling
    -0.62
    POSITIVE LOGITS
    clus
    0.77
     welcoming
    0.75
     approving
    0.72
     attracting
    0.71
     proclaiming
    0.70
    nered
    0.68
    ignt
    0.67
    assert
    0.67
    looking
    0.67
     woo
    0.66
    Act Density 0.243%

    No Known Activations