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

    Neuronpedia

    INDEX
    Explanations

    specific Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    specific annotations or metadata related to concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emb
    -0.80
     Esper
    -0.76
    UX
    -0.75
     emb
    -0.75
    cham
    -0.74
     Chung
    -0.74
    ume
    -0.72
     Amit
    -0.71
    gaard
    -0.68
    achus
    -0.68
    POSITIVE LOGITS
    R
    1.49
    Rs
    1.34
     R
    1.29
     Ri
    1.29
    r
    1.26
    RP
    1.24
    RS
    1.24
     Rak
    1.24
     RI
    1.20
    RR
    1.19
    Act Density 0.674%

    No Known Activations