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

    Neuronpedia

    INDEX
    Explanations

    references to computer science or related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erialize
    -0.18
    eu
    -0.17
    orsch
    -0.16
    алÑĭ
    -0.16
    TY
    -0.16
    usercontent
    -0.16
    oles
    -0.16
    поÑĢ
    -0.16
    elf
    -0.15
    cala
    -0.14
    POSITIVE LOGITS
    IRO
    0.23
    fulness
    0.16
     Lewis
    0.16
     CS
    0.15
     Harrison
    0.15
    atra
    0.15
    aÅĻ
    0.15
     bet
    0.14
    erti
    0.14
    utom
    0.14
    Act Density 0.016%

    No Known Activations