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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the existence or state of affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥįãĥ«
    -0.15
     Kaplan
    -0.14
    ksam
    -0.13
     Platt
    -0.13
    vi
    -0.13
    Ł³
    -0.13
    728
    -0.13
    osten
    -0.13
    ãģ£ãģ±
    -0.13
    benh
    -0.13
    POSITIVE LOGITS
    SharedPointer
    0.16
    otland
    0.15
    ditor
    0.14
    steen
    0.14
     RTP
    0.14
     flirting
    0.13
    íĮIJ
    0.13
    edList
    0.13
     ents
    0.13
    :CGRect
    0.13
    Act Density 0.230%

    No Known Activations