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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wrap" and its variations, indicating a focus on wrapping or enclosing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iac
    -0.17
     Rig
    -0.15
    utely
    -0.15
    cup
    -0.14
    923
    -0.14
    otti
    -0.14
    eka
    -0.14
    ltra
    -0.14
    WER
    -0.14
    amespace
    -0.14
    POSITIVE LOGITS
    around
    0.26
    -around
    0.26
    .wrap
    0.26
    .Wrap
    0.24
     wrap
    0.24
     Wrap
    0.22
    .wr
    0.20
     wrapped
    0.20
     wrapping
    0.20
    owski
    0.19
    Act Density 0.017%

    No Known Activations