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

    Neuronpedia

    INDEX
    Explanations

    collective concerns and opinions about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qus
    -0.82
    osate
    -0.73
    ibur
    -0.67
    OGR
    -0.66
    edia
    -0.66
    plete
    -0.65
    »Ĵ
    -0.63
    iliate
    -0.61
    urrection
    -0.61
     lure
    -0.60
    POSITIVE LOGITS
     except
    1.02
     alike
    0.86
    ses
    0.80
     equally
    0.74
    except
    0.73
     agrees
    0.72
    winner
    0.68
     equal
    0.66
    equal
    0.66
    share
    0.61
    Act Density 1.012%

    No Known Activations