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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or settlements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reaching agreements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tud
    -0.70
     sake
    -0.66
     followed
    -0.66
     alike
    -0.65
     alone
    -0.61
     preceded
    -0.60
     Titus
    -0.59
    sbm
    -0.58
     ensued
    -0.58
     trailed
    -0.58
    POSITIVE LOGITS
     heights
    1.01
    levels
    0.88
    iggurat
    0.86
    ĸļ
    0.85
    lyak
    0.84
     milestone
    0.82
     plateau
    0.80
    utenberg
    0.79
     pinnacle
    0.79
     conclusion
    0.79
    Act Density 0.143%

    No Known Activations