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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alim
    -0.15
    umi
    -0.15
    rud
    -0.15
    akte
    -0.15
    .getValueAt
    -0.14
    esting
    -0.14
    exus
    -0.14
    .cb
    -0.14
    ervo
    -0.14
    kili
    -0.14
    POSITIVE LOGITS
    deaux
    0.18
    /if
    0.16
     merely
    0.16
     just
    0.15
     simply
    0.15
     something
    0.14
    something
    0.13
    hi
    0.13
     atol
    0.13
    [it
    0.13
    Act Density 0.023%

    No Known Activations