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

    Neuronpedia

    INDEX
    Explanations

    references to blocks within a data structure or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %)$
    -0.86
     Ory
    -0.79
    ükemmel
    -0.76
     Esau
    -0.75
     RNN
    -0.72
     Keating
    -0.71
    stdarg
    -0.71
     cheiro
    -0.69
     Ariana
    -0.68
    cuál
    -0.67
    POSITIVE LOGITS
     block
    2.87
     Block
    2.83
    block
    2.78
     BLOCK
    2.78
     blocks
    2.74
    Block
    2.67
    BLOCK
    2.59
     Blocks
    2.58
    blocks
    2.52
    Blocks
    2.33
    Act Density 0.027%

    No Known Activations