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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities done with others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.81
    hood
    -0.75
    iture
    -0.71
    soon
    -0.71
     (.
    -0.70
    itures
    -0.69
    sburg
    -0.68
     unless
    -0.68
     furthermore
    -0.68
    meal
    -0.67
    POSITIVE LOGITS
     impunity
    1.31
    stood
    1.30
     colleagues
    1.01
     regard
    1.00
     regards
    1.00
     him
    0.99
     us
    0.97
     pals
    0.94
     coworkers
    0.92
     them
    0.91
    Act Density 0.208%

    No Known Activations