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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or partnership

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the phrase "teamed up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     irregular
    -0.81
     NASL
    -0.71
     responsive
    -0.64
     Brazilian
    -0.64
     oppressed
    -0.63
     examination
    -0.62
     disturbance
    -0.62
     residential
    -0.62
     marginalized
    -0.62
     Annex
    -0.62
    POSITIVE LOGITS
     teamed
    2.50
     Heller
    1.22
     wielded
    0.98
    assic
    0.97
     mash
    0.96
     clashed
    0.90
     wield
    0.87
    hiba
    0.87
     lik
    0.85
    handedly
    0.84
    Act Density 0.044%

    No Known Activations