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

    Neuronpedia

    INDEX
    Explanations

    scientific observations and findings that denote noteworthy or novel results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.50
    ↵↵
    -0.50
    :
    -0.48
    ;
    -0.47
    .
    -0.45
    <bos>
    -0.44
    -
    -0.44
    UnknownFields
    -0.43
    /
    -0.43
    <eos>
    -0.43
    POSITIVE LOGITS
     createSlice
    1.01
     ComVisible
    0.84
    vaders
    0.80
     autorytatywna
    0.80
     Ganzen
    0.79
    complexContent
    0.79
    stuffs
    0.78
    =$?
    0.78
     CWE
    0.76
     تضيفلها
    0.76
    Act Density 0.571%

    No Known Activations