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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with the word "Those"

    oai_token-act-pair · gpt-3.5-turbo

    references to "those" or entities being discussed in the context of various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILY
    -0.86
    shapeshifter
    -0.78
    ointment
    -0.74
    orate
    -0.73
    irth
    -0.72
    Drag
    -0.72
     ..."
    -0.70
    iness
    -0.68
    ice
    -0.67
    enegger
    -0.66
    POSITIVE LOGITS
     wishing
    0.83
     pesky
    0.82
     kinds
    0.81
     thoughts
    0.81
     interested
    0.80
     voices
    0.80
     eyebrows
    0.72
     statements
    0.71
     sights
    0.71
     fellows
    0.70
    Act Density 0.050%

    No Known Activations