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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate analytical or evaluative actions related to theories and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     persever
    -0.14
    ëĬ¥
    -0.13
    stub
    -0.13
     dub
    -0.13
     Oro
    -0.13
    rias
    -0.13
     Hier
    -0.12
    ãģ°ãģĭãĤĬ
    -0.12
    ÏĥÏĦά
    -0.12
    usch
    -0.12
    POSITIVE LOGITS
    ingham
    0.18
    okus
    0.17
    ãĥ³ãĥĸ
    0.16
    ocus
    0.16
    ploy
    0.14
    acas
    0.14
    éĨ
    0.14
    asca
    0.14
    ande
    0.14
    ourt
    0.13
    Act Density 0.126%

    No Known Activations