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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "training" and related terms

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

    "training"

    np_acts-logits-general · gemini-2.0-flash

    training followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Antara
    -0.55
    Твор
    -0.55
    mbol
    -0.54
    ViewInit
    -0.54
    }),
    -0.54
    SerializedName
    -0.53
    complexContent
    -0.51
    HHHHHHHH
    -0.50
    тельства
    -0.50
    otone
    -0.50
    POSITIVE LOGITS
    DebuggerNonUser
    0.72
     wheels
    0.70
    UrlResolution
    0.69
    wheels
    0.68
     propOrder
    0.67
     programmes
    0.63
    RetentionPolicy
    0.63
     sessions
    0.63
     regimens
    0.62
    wreck
    0.62
    Act Density 0.084%

    No Known Activations