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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and relational dynamics among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stub
    -0.08
    claimer
    -0.07
    acie
    -0.07
    æĹ¢
    -0.07
     zwar
    -0.07
     EDGE
    -0.07
    EDGE
    -0.07
    almost
    -0.07
    achable
    -0.07
    uther
    -0.07
    POSITIVE LOGITS
     necessarily
    0.21
     anymore
    0.13
     any
    0.11
     suddenly
    0.10
     somehow
    0.09
     couldn
    0.09
     automatically
    0.09
    any
    0.09
    ecessarily
    0.09
     ever
    0.08
    Act Density 0.039%

    No Known Activations