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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to matching or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.89
    cation
    -0.73
    uler
    -0.72
    cember
    -0.71
    Discuss
    -0.70
    duc
    -0.67
     trave
    -0.66
    SO
    -0.66
    ciplinary
    -0.64
     Discuss
    -0.63
    POSITIVE LOGITS
    amorph
    0.85
     expectations
    0.77
    sticks
    0.75
    tle
    0.74
    stick
    0.72
     theirs
    0.71
    enance
    0.70
     up
    0.69
     ours
    0.68
     yours
    0.67
    Act Density 0.035%

    No Known Activations