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

    Neuronpedia

    INDEX
    Explanations

    code structures and symbols used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſſung
    -0.97
    <unused68>
    -0.96
    <unused14>
    -0.96
    <unused52>
    -0.96
    <unused23>
    -0.96
    <unused17>
    -0.96
    <unused47>
    -0.96
    <unused51>
    -0.96
    [@BOS@]
    -0.96
    <unused16>
    -0.96
    POSITIVE LOGITS
    ;
    0.44
    .
    0.44
     
    0.42
    1
    0.40
     ;
    0.40
    3
    0.37
    ↵
    0.36
    2
    0.35
    ↵↵
    0.35
    5
    0.34
    Act Density 0.493%

    No Known Activations