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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurable and quantifiable attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.19
    atar
    -0.17
    ampa
    -0.16
    olen
    -0.15
    erot
    -0.15
    elpers
    -0.15
    occo
    -0.15
     dry
    -0.15
    ÏĢοÏĦε
    -0.14
    undle
    -0.14
    POSITIVE LOGITS
     Orwell
    0.15
    CEED
    0.14
    alis
    0.14
    inous
    0.14
    ÑĤÑĶ
    0.14
    839
    0.13
     Entertainment
    0.13
    á»ĥn
    0.13
     LIC
    0.13
    IVAL
    0.13
    Act Density 0.024%

    No Known Activations