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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions among characters with emotional undertones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.75
     tantum
    -0.73
     ſtate
    -0.69
     purpoſe
    -0.68
     houſe
    -0.67
     Monfieur
    -0.67
     habet
    -0.64
     orgánica
    -0.63
     themſelves
    -0.61
     slutet
    -0.59
    POSITIVE LOGITS
     looked
    0.59
     hesit
    0.53
     struggled
    0.52
     ContentValues
    0.51
     glared
    0.50
    LookAnd
    0.50
    HttpFoundation
    0.49
     pondered
    0.49
     wondered
    0.48
     tartalomajánló
    0.48
    Act Density 0.073%

    No Known Activations