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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.17
    onian
    -0.16
    è¿·
    -0.16
    urator
    -0.16
     âĹĦ
    -0.16
    burgh
    -0.15
    mith
    -0.15
    áct
    -0.15
    licas
    -0.15
    lify
    -0.15
    POSITIVE LOGITS
    ings
    0.26
    able
    0.23
    lement
    0.20
    ability
    0.18
     ing
    0.18
    -your
    0.18
    back
    0.17
    Ing
    0.17
    INGS
    0.17
    -all
    0.16
    Act Density 0.144%

    No Known Activations