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

    Neuronpedia

    INDEX
    Explanations

    commonalities or shared characteristics between people or groups

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to shared beliefs or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anish
    -0.73
    aunder
    -0.72
    cember
    -0.70
    ī
    -0.68
    llers
    -0.67
    ²¾
    -0.66
    icans
    -0.65
     desper
    -0.65
    uren
    -0.62
    iffe
    -0.62
    POSITIVE LOGITS
     similarities
    1.00
     responsibility
    0.84
    cro
    0.79
     responsibilities
    0.76
     characteristics
    0.74
     resemb
    0.73
     interests
    0.73
    ership
    0.69
     resemblance
    0.69
     sentiments
    0.68
    Act Density 0.039%

    No Known Activations