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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe components or parts of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.80
    soType
    -0.78
     undermin
    -0.72
     override
    -0.70
     mosqu
    -0.69
     showc
    -0.68
    itability
    -0.67
    visor
    -0.65
    orah
    -0.64
    aware
    -0.64
    POSITIVE LOGITS
     sorts
    0.78
    umbn
    0.70
     Cly
    0.67
     varying
    0.63
     Eucl
    0.63
    éĹĺ
    0.62
    course
    0.61
    ++++++++
    0.61
     course
    0.59
     three
    0.59
    Act Density 0.056%

    No Known Activations