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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating influence and comparison between differing concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _blob
    -0.15
    terra
    -0.15
     disposable
    -0.15
    utin
    -0.14
     Heap
    -0.14
     expend
    -0.13
    ensely
    -0.13
    ertos
    -0.13
     SINGLE
    -0.13
    estring
    -0.13
    POSITIVE LOGITS
     greater
    0.29
     considerable
    0.28
    greater
    0.26
     greatest
    0.23
     substantial
    0.22
     maximal
    0.22
     strong
    0.22
     acute
    0.21
     immense
    0.21
     severe
    0.21
    Act Density 0.203%

    No Known Activations