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

    Neuronpedia

    INDEX
    Explanations

    function calls and references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `.getWidth` after strings

    np_acts-logits-general · gemini-2.0-flash

    string that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.55
    ,
    -0.51
     a
    -0.51
     also
    -0.49
     for
    -0.49
    </em>
    -0.49
     with
    -0.48
    </i>
    -0.47
    ra
    -0.46
    art
    -0.46
    POSITIVE LOGITS
     Efq
    0.95
    UnsafeEnabled
    0.92
     myſelf
    0.88
     Cæsar
    0.83
     Majefty
    0.82
     Jefus
    0.81
     ſind
    0.80
     Houſe
    0.80
     leaſt
    0.80
     Monfieur
    0.79
    Act Density 0.295%

    No Known Activations