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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or settlements between parties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreements, deals, or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     followed
    -0.75
     preceded
    -0.71
    watching
    -0.68
     arose
    -0.67
     endured
    -0.66
     sake
    -0.65
    sbm
    -0.64
     transpired
    -0.63
     existed
    -0.62
     ensued
    -0.62
    POSITIVE LOGITS
     heights
    1.05
     conclusion
    0.97
     conclusions
    0.89
     milestone
    0.89
     plateau
    0.86
     bounds
    0.86
     pinnacle
    0.85
     threshold
    0.81
     depths
    0.80
    limit
    0.80
    Act Density 0.088%

    No Known Activations