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

    Neuronpedia

    INDEX
    Explanations

    question marks indicating inquiries or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.57
     a
    -0.53
    .
    -0.50
    ,
    -0.50
     is
    -0.48
    sendFile
    -0.47
     I
    -0.46
     -
    -0.45
     long
    -0.44
     K
    -0.44
    POSITIVE LOGITS
    ?}
    1.50
    ?
    1.48
    ?"
    1.46
    %?
    1.44
    ?".
    1.42
    }?
    1.41
    ?”
    1.40
    ?’
    1.40
    ?'
    1.38
    ?";
    1.37
    Act Density 0.120%

    No Known Activations