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

    Neuronpedia

    INDEX
    Explanations

    numerical values or identifiers, particularly those that follow a specific format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enc
    -0.19
    camp
    -0.17
    ple
    -0.17
    alf
    -0.15
    amp
    -0.15
    ens
    -0.15
    ared
    -0.14
    vara
    -0.14
     lapse
    -0.14
    eda
    -0.14
    POSITIVE LOGITS
    ussen
    0.20
    quette
    0.19
    untime
    0.17
    rophe
    0.17
    agma
    0.16
    woord
    0.16
    rak
    0.15
    ırak
    0.15
    thew
    0.15
    ments
    0.15
    Act Density 0.111%

    No Known Activations