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

    Neuronpedia

    INDEX
    Explanations

    instances where something is described or compared as being equal to or similar to something else in terms of quality or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize quantification and comparison of experiences or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olded
    -0.69
    eele
    -0.67
    gee
    -0.66
    eka
    -0.66
    eri
    -0.65
    ammy
    -0.64
    orb
    -0.64
     CFR
    -0.62
    aternity
    -0.62
    recomm
    -0.61
    POSITIVE LOGITS
     imaginable
    1.31
     conceivable
    0.97
    except
    0.85
     except
    0.84
    nut
    0.81
     whatsoever
    0.70
     facets
    0.69
    ãĤ«
    0.68
     sane
    0.68
    THING
    0.67
    Act Density 0.100%

    No Known Activations