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

    Neuronpedia

    INDEX
    Explanations

    phrases that signal condition, transition, or contrast in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    daq
    -0.15
    xo
    -0.15
    ейÑģÑĤв
    -0.14
     ÑĢÑĥб
    -0.14
    onn
    -0.14
     nostr
    -0.14
    ayo
    -0.14
    .userInteractionEnabled
    -0.13
    pdb
    -0.13
    rs
    -0.13
    POSITIVE LOGITS
     said
    0.49
    said
    0.39
     Said
    0.35
     aside
    0.34
     being
    0.33
    being
    0.28
    Being
    0.24
     Being
    0.24
     dicho
    0.24
     sendo
    0.23
    Act Density 0.048%

    No Known Activations