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

    Neuronpedia

    INDEX
    Explanations

    references to collective experiences or shared knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥģ
    -0.16
    igr
    -0.15
    etti
    -0.15
    utes
    -0.14
    ighth
    -0.14
    idon
    -0.14
    rees
    -0.13
    VM
    -0.13
    (es
    -0.13
    udi
    -0.13
    POSITIVE LOGITS
     reminded
    0.17
     remind
    0.16
     awareness
    0.15
     speak
    0.15
     rop
    0.15
     parl
    0.15
     aware
    0.14
    OfString
    0.14
    aware
    0.14
     Cass
    0.14
    Act Density 0.031%

    No Known Activations