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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diplomatic assignments and preparations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that summarize actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clot
    -0.75
     arm
    -0.72
     ko
    -0.68
     ownership
    -0.65
     silent
    -0.64
    ideshow
    -0.64
     footing
    -0.63
     retracted
    -0.63
     mercy
    -0.63
     gunfire
    -0.62
    POSITIVE LOGITS
     Whilst
    0.88
     Especially
    0.87
     Such
    0.87
     Particularly
    0.85
    htaking
    0.84
    sbm
    0.83
    stellar
    0.81
     Specifically
    0.81
     Examples
    0.78
     Unfortunately
    0.78
    Act Density 1.266%

    No Known Activations