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

    Neuronpedia

    INDEX
    Explanations

    instances of action and interaction in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.19
     III
    -0.19
    II
    -0.19
    III
    -0.18
     II
    -0.16
     VII
    -0.15
    -II
    -0.15
     VIII
    -0.15
    IV
    -0.14
    assin
    -0.14
    POSITIVE LOGITS
     me
    0.59
     yours
    0.42
     moi
    0.39
     us
    0.37
     Yours
    0.37
    me
    0.32
     менÑı
    0.28
     mnie
    0.27
     mij
    0.27
     mine
    0.27
    Act Density 0.218%

    No Known Activations