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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical analysis and research methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.58
    ↵↵
    -0.55
    2
    -0.54
    ↵
    -0.53
    1
    -0.52
    0
    -0.51
     and
    -0.46
    3
    -0.46
    is
    -0.46
    ,
    -0.45
    POSITIVE LOGITS
    <unused52>
    1.84
    <unused8>
    1.83
    <unused14>
    1.82
    [@BOS@]
    1.82
    <unused51>
    1.81
    <unused41>
    1.81
    <unused68>
    1.81
    <unused74>
    1.81
    <unused3>
    1.81
    <unused28>
    1.81
    Act Density 1.431%

    No Known Activations