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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical descriptions or specifications in programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.17
     exactly
    -0.17
    achel
    -0.15
     fod
    -0.15
     ÑĦакÑĤи
    -0.14
     apenas
    -0.14
    terr
    -0.14
    åħ¶å®ŀ
    -0.13
    æīį
    -0.13
    appa
    -0.13
    POSITIVE LOGITS
    IRO
    0.17
    ely
    0.16
    idad
    0.15
     Depends
    0.15
     benchmark
    0.14
    Same
    0.14
    ELY
    0.14
     Same
    0.14
    ike
    0.14
    ly
    0.14
    Act Density 0.130%

    No Known Activations