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

    Neuronpedia

    INDEX
    Explanations

    references to personal ownership or possessive language

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

    possession or belonging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.51
     purpoſe
    -0.47
     ſtre
    -0.44
    eamiento
    -0.43
    GEBURTSDATUM
    -0.42
     فريبيس
    -0.42
     snippetHide
    -0.42
    untamiento
    -0.42
     enfans
    -0.42
    AutoScaleMode
    -0.42
    POSITIVE LOGITS
    なんと
    0.74
    rungsseite
    0.57
     possess
    0.51
     own
    0.51
    RegressionTest
    0.51
     possesses
    0.50
     reside
    0.49
    にあります
    0.46
     enchanted
    0.46
     啦
    0.46
    Act Density 0.005%

    No Known Activations