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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain names

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and university names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ococ
    -0.74
     Malk
    -0.72
     Osh
    -0.70
    roup
    -0.70
    683
    -0.69
     asbestos
    -0.67
     Shapiro
    -0.67
     Oslo
    -0.67
     Leh
    -0.66
     Palestine
    -0.66
    POSITIVE LOGITS
    D
    1.42
    DD
    1.38
    d
    1.34
    Ds
    1.31
    dor
    1.26
    ds
    1.26
    dt
    1.25
    DR
    1.23
    DM
    1.23
    da
    1.22
    Act Density 1.213%

    No Known Activations