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

    Neuronpedia

    INDEX
    Explanations

    references to physical movements and actions

    oai_token-act-pair · gpt-3.5-turbo

    actions and events related to performance or theatrical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.66
    riott
    -0.62
    actionDate
    -0.59
    htaking
    -0.55
     depends
    -0.55
    uncture
    -0.55
     lately
    -0.54
     nowadays
    -0.53
    insula
    -0.53
     )]
    -0.50
    POSITIVE LOGITS
     stating
    0.89
     saying
    0.86
     causing
    0.85
    .
    0.85
     ensued
    0.84
     shouting
    0.83
     followed
    0.83
     yelling
    0.83
     assum
    0.82
     thanking
    0.82
    Act Density 0.642%

    No Known Activations