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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations where actions are taken based on certain criteria or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Once followed by you or we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MockMvc
    -0.43
     liar
    -0.37
    DUC
    -0.36
     oprot
    -0.36
    NameIn
    -0.35
    bukkit
    -0.35
    èse
    -0.35
    Попис
    -0.34
    edict
    -0.34
    InOut
    -0.34
    POSITIVE LOGITS
    Once
    0.98
     Once
    0.96
    once
    0.91
     ONCE
    0.82
    ONCE
    0.81
     once
    0.79
     Sobald
    0.79
     sobald
    0.75
    After
    0.71
     Nachdem
    0.70
    Act Density 0.024%

    No Known Activations