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

    Neuronpedia

    INDEX
    Explanations

    words related to analyzing and discussing thoughts, opinions, and observations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opinions and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.68
     Stores
    -0.61
    hold
    -0.60
    leasing
    -0.60
    inventory
    -0.59
     peril
    -0.59
    red
    -0.57
    scope
    -0.57
    gm
    -0.57
    existent
    -0.57
    POSITIVE LOGITS
     rant
    0.77
     listener
    0.74
    itone
    0.73
     thanking
    0.73
     smack
    0.72
     aloud
    0.70
    Interstitial
    0.70
     paralysis
    0.70
     sugg
    0.68
     sarcast
    0.68
    Act Density 0.276%

    No Known Activations