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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to memory management and pointer operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $[
    -0.65
    ][$
    -0.64
    :['
    -0.62
    =["
    -0.62
    >${
    -0.59
    [$
    -0.57
    ?[
    -0.57
     [,
    -0.56
    ?...
    -0.56
    ]?.
    -0.55
    POSITIVE LOGITS
     &(
    1.04
    sizeof
    1.02
     &
    0.97
     sizeof
    0.96
    &(
    0.94
    offsetof
    0.91
    NULL
    0.85
     (&
    0.85
     *(
    0.83
     NULL
    0.82
    Act Density 0.474%

    No Known Activations