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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of hidden agendas or underlying motives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĽ
    -0.16
    hiba
    -0.15
    verture
    -0.15
    argas
    -0.14
    endcode
    -0.14
     subrange
    -0.14
    ãĥ³ãĤº
    -0.14
     neh
    -0.13
    оÑĢаз
    -0.13
    weed
    -0.13
    POSITIVE LOGITS
    erm
    0.16
     Nielsen
    0.15
    455
    0.15
    ÐŁÐļ
    0.14
     Convention
    0.14
    ris
    0.14
    ape
    0.14
    378
    0.13
    åĩ
    0.13
    all
    0.13
    Act Density 0.248%

    No Known Activations