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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or possibilities

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

    it is possible to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offense
    -0.38
     fellow
    -0.38
     its
    -0.36
     NEIGH
    -0.35
     it
    -0.35
    йо
    -0.34
    signOut
    -0.34
     promotion
    -0.34
     SOUT
    -0.33
     durer
    -0.33
    POSITIVE LOGITS
     ניתן
    0.73
     canst
    0.69
     można
    0.68
    ניתן
    0.66
     müm
    0.65
    можно
    0.63
     אפשר
    0.62
    สามารถ
    0.62
    Vidite
    0.61
    MethodManager
    0.61
    Act Density 0.019%

    No Known Activations