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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or indentation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.40
     ब्रेकडाउन
    -1.23
    ftagPool
    -1.17
     vooz
    -1.16
    ſelben
    -1.16
     $_"
    -1.14
    [@BOS@]
    -1.14
    <unused68>
    -1.14
    <unused52>
    -1.13
    ſſung
    -1.13
    POSITIVE LOGITS
    //
    0.84
                            
    0.65
    (
    0.62
                                
    0.60
                        
    0.58
                      
    0.58
                             
    0.57
    0.57
    0.57
    0.56
    Act Density 1.190%

    No Known Activations