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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases and expressions of excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recently
    -0.25
     Recently
    -0.22
    recent
    -0.22
     recent
    -0.21
    Recently
    -0.20
    æľĢè¿ij
    -0.19
     lately
    -0.17
    TOTYPE
    -0.15
    monthly
    -0.15
     ìµľê·¼
    -0.14
    POSITIVE LOGITS
    Overall
    0.25
     Overall
    0.24
     Afterwards
    0.23
     everyone
    0.21
     overall
    0.21
     afterwards
    0.21
    After
    0.20
     after
    0.19
     Everyone
    0.19
    Everyone
    0.19
    Act Density 0.207%

    No Known Activations