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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and identities of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wire
    -0.19
     Wire
    -0.16
    ripp
    -0.15
    िब
    -0.15
     Horizon
    -0.15
    ocab
    -0.14
     Wiring
    -0.14
    915
    -0.14
     Riverside
    -0.14
    ogne
    -0.13
    POSITIVE LOGITS
    cul
    0.16
    urator
    0.15
    aise
    0.15
     cr
    0.14
    ASI
    0.14
    pios
    0.14
    aises
    0.14
    atories
    0.14
    aten
    0.14
    wnd
    0.14
    Act Density 0.004%

    No Known Activations