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

    Neuronpedia

    INDEX
    Explanations

    phrases conveying likelihood or suggestive outcomes

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

    likely to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paravant
    -0.47
     sumpay
    -0.38
     بط
    -0.38
     sofort
    -0.37
     @"/
    -0.37
     mierda
    -0.35
     simplesmente
    -0.34
    Entrada
    -0.34
     auparavant
    -0.34
     návr
    -0.33
    POSITIVE LOGITS
     فريبيس
    0.68
     ſind
    0.66
    GEBURTSDATUM
    0.59
    Cyfarwyddwr
    0.57
    apunov
    0.53
     <<<<<<<<<<<<<<
    0.52
     ſei
    0.51
     CWE
    0.51
     lenker
    0.50
    HostException
    0.50
    Act Density 0.228%

    No Known Activations