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

    Neuronpedia

    INDEX
    Explanations

    instances of output statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aza
    -0.64
    melde
    -0.63
    𝓬
    -0.57
     
    -0.57
    <i>
    -0.57
    着
    -0.56
    anu
    -0.56
     меха
    -0.55
    eria
    -0.55
     até
    -0.55
    POSITIVE LOGITS
     endl
    2.63
    endl
    2.47
     يتيمه
    1.51
     Efq
    1.22
    argout
    0.94
    ſelf
    0.94
     Monfieur
    0.93
     poffible
    0.93
    AndEndTag
    0.92
     bezeichneter
    0.90
    Act Density 0.042%

    No Known Activations