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

    Neuronpedia

    INDEX
    Explanations

    terms related to structured support systems and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     же
    -0.18
    arse
    -0.17
    enk
    -0.15
    ategorical
    -0.14
    bff
    -0.14
    .RESET
    -0.14
    .mods
    -0.14
    aves
    -0.14
    ardi
    -0.13
     nameof
    -0.13
    POSITIVE LOGITS
     Heller
    0.15
    sian
    0.14
    ulla
    0.14
     Prov
    0.14
    κοÏį
    0.13
    ume
    0.13
    ederland
    0.13
    hay
    0.13
    ullo
    0.13
     Wel
    0.13
    Act Density 1.267%

    No Known Activations