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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news, announcements, and decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to significant announcements or cancellations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.83
    Qaida
    -0.70
    ospels
    -0.69
    raits
    -0.68
    roleum
    -0.66
    Texture
    -0.65
     Trails
    -0.65
     varieties
    -0.64
    Frameworks
    -0.64
    doi
    -0.64
    POSITIVE LOGITS
     decision
    1.06
     cancellation
    1.00
     announcement
    0.99
     reasoning
    0.96
     termination
    0.93
     fiasco
    0.92
     disappointment
    0.91
     debacle
    0.90
     mistake
    0.90
     setback
    0.90
    Act Density 1.070%

    No Known Activations