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

    Neuronpedia

    INDEX
    Explanations

    references to copying and pasting content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leys
    -0.19
    utsch
    -0.18
    lems
    -0.18
    sg
    -0.16
    ness
    -0.16
    sv
    -0.16
    sWith
    -0.16
    .googlecode
    -0.16
    lein
    -0.16
    semble
    -0.15
    POSITIVE LOGITS
    .deepcopy
    0.38
    cat
    0.36
    cats
    0.32
    -cat
    0.29
    editing
    0.29
     paste
    0.29
    writing
    0.27
    Paste
    0.26
    wright
    0.25
    writer
    0.24
    Act Density 0.030%

    No Known Activations