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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to negative events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions that emphasize the phrase "to say the least."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.78
     anew
    -0.70
    born
    -0.68
     ourselves
    -0.66
    Accessory
    -0.64
     Citation
    -0.60
    FTWARE
    -0.60
    selves
    -0.60
    unc
    -0.59
    Demand
    -0.58
    POSITIVE LOGITS
     needle
    0.64
     fishes
    0.62
     roses
    0.61
     chin
    0.59
     artist
    0.59
     fitt
    0.59
     wire
    0.58
     proverbial
    0.56
     worse
    0.55
     heals
    0.55
    Act Density 0.116%

    No Known Activations