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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating future actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hlav
    -0.15
     ampl
    -0.14
    æĥ³åĪ°
    -0.13
    opsis
    -0.13
     Morg
    -0.13
    ãĥĶãĥ¼
    -0.13
    ansom
    -0.13
    ì§
    -0.13
    بات
    -0.13
     recently
    -0.13
    POSITIVE LOGITS
     help
    0.23
     helps
    0.20
     helfen
    0.19
    help
    0.19
     mean
    0.18
     complement
    0.18
     enable
    0.17
     initially
    0.17
     result
    0.16
    Help
    0.16
    Act Density 0.105%

    No Known Activations