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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement strategies and their impacts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     sc
    -0.53
    UFF
    -0.53
     незавершена
    -0.52
    laven
    -0.52
    getline
    -0.51
    urato
    -0.49
    sizeCache
    -0.48
    HasBeenSet
    -0.48
    GOTREF
    -0.48
    ULF
    -0.48
    POSITIVE LOGITS
    UserScript
    0.66
    CGRectMake
    0.53
    getRuntime
    0.53
     CURIAM
    0.51
    })$}
    0.49
    Tikang
    0.49
    原标题
    0.49
    0.49
    '],$
    0.48
     ISNI
    0.48
    Act Density 0.595%

    No Known Activations