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

    Neuronpedia

    INDEX
    Explanations

    sentences involving dialogue between characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     synerg
    -0.88
     targeted
    -0.81
     territorial
    -0.80
     favor
    -0.79
     spir
    -0.78
     consolidation
    -0.75
     migr
    -0.74
     fragmented
    -0.74
     dubbed
    -0.73
     impacts
    -0.73
    POSITIVE LOGITS
    Yeah
    1.28
    Okay
    1.26
    Yes
    1.26
    What
    1.21
    Oh
    1.17
    Why
    1.15
    Hey
    1.15
    Who
    1.15
    yeah
    1.14
    Sure
    1.13
    Act Density 0.103%

    No Known Activations