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

    Neuronpedia

    INDEX
    Explanations

    references to razors and related terms in various contexts

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

    "razor" or cutting

    np_acts-logits-general · gemini-2.0-flash

    razor blades and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resolução
    -0.52
     Bus
    -0.50
    rtz
    -0.49
    XmlAccessorType
    -0.48
    ymi
    -0.48
    hatic
    -0.47
    円
    -0.46
    ess
    -0.45
    copus
    -0.44
     Me
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    1.34
    InjectAttribute
    0.85
     فريبيس
    0.77
    Razor
    0.73
     Razor
    0.72
     Efq
    0.72
    ScopeManager
    0.71
     houſe
    0.70
     pleaſure
    0.69
     myſelf
    0.67
    Act Density 0.062%

    No Known Activations