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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arat
    -0.16
    eres
    -0.15
     mars
    -0.14
    ahir
    -0.14
    ecut
    -0.14
    ockey
    -0.14
     Pessoa
    -0.14
    å¶
    -0.13
     dau
    -0.13
    lasses
    -0.13
    POSITIVE LOGITS
    nothrow
    0.16
    iec
    0.14
    ANEL
    0.14
    帽
    0.14
     Conc
    0.14
    มà¸Ń
    0.14
    iero
    0.14
    âng
    0.14
    helm
    0.14
    opoulos
    0.14
    Act Density 0.032%

    No Known Activations