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

    Neuronpedia

    INDEX
    Explanations

    functions and statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Out
    -0.15
     dis
    -0.14
     deliberate
    -0.14
     L
    -0.14
    yscale
    -0.14
     B
    -0.14
     Long
    -0.13
    eba
    -0.13
    ono
    -0.13
     R
    -0.13
    POSITIVE LOGITS
    963
    0.17
        ↵
    0.16
     λÏĮγ
    0.16
     Collider
    0.16
    aldi
    0.15
    	↵
    0.14
    	d
    0.14
    sher
    0.14
            ↵
    0.14
    llib
    0.14
    Act Density 0.259%

    No Known Activations