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

    Neuronpedia

    INDEX
    Explanations

    phrases related to app permissions and user prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĹãĤĩ
    -0.15
    Carbon
    -0.14
    engin
    -0.14
    reh
    -0.14
    vre
    -0.14
     mart
    -0.14
    _TMP
    -0.14
    Mart
    -0.14
    normalize
    -0.14
     toe
    -0.14
    POSITIVE LOGITS
    uns
    0.19
    UNS
    0.16
    inz
    0.16
    _jet
    0.16
    estring
    0.16
    anj
    0.15
     Successfully
    0.15
     Uns
    0.15
    cxx
    0.15
    lar
    0.15
    Act Density 0.052%

    No Known Activations