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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endon
    -0.16
    iali
    -0.15
    .SOCK
    -0.15
    anks
    -0.14
    AdapterFactory
    -0.14
    plusplus
    -0.13
     POLITICO
    -0.13
    asan
    -0.13
    ivot
    -0.13
    indsay
    -0.13
    POSITIVE LOGITS
    Sibling
    0.16
    rh
    0.14
    Stamped
    0.14
    uce
    0.14
    Lie
    0.14
    _ATT
    0.14
    spread
    0.14
    æĻĵ
    0.14
    çݲ
    0.13
     considering
    0.13
    Act Density 0.068%

    No Known Activations