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

    Neuronpedia

    INDEX
    Explanations

    references to programming and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CodedInputStream
    -0.94
    rungsseite
    -0.81
    InitVars
    -0.78
     שוליים
    -0.76
    Portale
    -0.76
     textStatus
    -0.71
     Efq
    -0.71
    bkz
    -0.70
     Theſe
    -0.70
    Bibliograf
    -0.69
    POSITIVE LOGITS
    <eos>
    0.83
    ↵↵
    0.64
     etc
    0.53
    etc
    0.49
    aki
    0.48
    ↵
    0.48
    ↵↵↵↵
    0.44
    ↵↵↵
    0.44
    uan
    0.42
    enumi
    0.41
    Act Density 0.025%

    No Known Activations