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

    Neuronpedia

    INDEX
    Explanations

    references to rescue actions or events

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

    rescue actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.49
    Tikang
    -0.49
     Lath
    -0.48
     Sheen
    -0.47
     zijne
    -0.46
     brow
    -0.46
    PreferredItem
    -0.46
    hasNext
    -0.45
    odacty
    -0.45
     Grams
    -0.45
    POSITIVE LOGITS
     rescue
    1.58
     rescued
    1.45
    rescue
    1.42
     rescues
    1.36
    Rescue
    1.33
     Rescue
    1.31
     rescuing
    1.27
     rescate
    1.27
     rescat
    1.25
    rescu
    1.16
    Act Density 0.005%

    No Known Activations