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

    Neuronpedia

    INDEX
    Explanations

    references to version numbers or numerical identifiers in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivi
    -0.16
    klad
    -0.15
     bü
    -0.15
     Jam
    -0.15
    Jam
    -0.15
    flux
    -0.15
     Yours
    -0.14
     flavor
    -0.14
     Tale
    -0.14
    han
    -0.13
    POSITIVE LOGITS
    arest
    0.18
    enda
    0.17
    frag
    0.16
    IBE
    0.16
    atters
    0.15
    leh
    0.15
     Frag
    0.15
    otify
    0.14
    lrt
    0.14
    PEG
    0.14
    Act Density 0.001%

    No Known Activations