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

    Neuronpedia

    INDEX
    Explanations

    transitions and casual discourse markers in informal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.60
    IUrlHelper
    -0.58
    ?";
    -0.57
     Wikimedijinoj
    -0.56
     Roskov
    -0.56
     Crow
    -0.54
    tvguidetime
    -0.53
    RegistryLite
    -0.53
    Халык
    -0.53
     samarbeid
    -0.52
    POSITIVE LOGITS
     Anyways
    0.95
     Anyway
    0.90
    Anyway
    0.87
    Anyways
    0.86
    Anyhow
    0.82
    anyway
    0.73
     anyways
    0.72
     anyhow
    0.69
     digress
    0.69
    튼
    0.68
    Act Density 0.140%

    No Known Activations