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

    Neuronpedia

    INDEX
    Explanations

    citations and references related to academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĢĨ
    -0.16
    osh
    -0.16
     Stereo
    -0.15
    ouns
    -0.15
    .builders
    -0.15
    Disposable
    -0.15
    awks
    -0.15
    ÑĥÑĩа
    -0.14
     bureau
    -0.14
    illery
    -0.14
    POSITIVE LOGITS
    elman
    0.17
    hazi
    0.17
    ãĤ¿ãĥ«
    0.17
     cru
    0.17
     cruise
    0.14
    çĶ£
    0.14
    esi
    0.14
    pod
    0.14
    .SYSTEM
    0.14
    eson
    0.14
    Act Density 0.098%

    No Known Activations