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

    Neuronpedia

    INDEX
    Explanations

    references to collective groups and their actions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tas
    -0.16
    .sul
    -0.16
    zin
    -0.15
    irá
    -0.15
    edik
    -0.15
    indle
    -0.15
    reten
    -0.14
    adb
    -0.14
    ulle
    -0.14
    ProcessEvent
    -0.14
    POSITIVE LOGITS
     talk
    0.21
     said
    0.20
     haven
    0.18
     Talk
    0.17
     need
    0.17
     saw
    0.17
    Talk
    0.16
     talked
    0.16
     talking
    0.16
     equivalents
    0.16
    Act Density 0.137%

    No Known Activations