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

    Neuronpedia

    INDEX
    Explanations

    references to the second-person pronoun "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fucked
    -0.15
    itos
    -0.15
    .XR
    -0.14
     cấp
    -0.14
    lop
    -0.14
    éd
    -0.14
    inus
    -0.14
    alfa
    -0.14
     pissed
    -0.14
    munition
    -0.14
    POSITIVE LOGITS
     sound
    0.21
     said
    0.20
     obviously
    0.20
     ok
    0.18
     two
    0.18
     mentioned
    0.18
     sir
    0.18
     mean
    0.17
     and
    0.16
     OK
    0.16
    Act Density 0.110%

    No Known Activations