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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is stepping up to take action or offer help

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts related to actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.92
    Moving
    -0.69
     Continued
    -0.67
    ahime
    -0.66
    Next
    -0.66
    Got
    -0.65
    drawn
    -0.64
    Links
    -0.63
    artifacts
    -0.63
    pointers
    -0.63
    POSITIVE LOGITS
     defend
    1.11
     compensate
    1.06
     participate
    1.03
     testify
    1.03
     meet
    1.01
     accommodate
    0.99
     haunt
    0.98
     celebrate
    0.96
     oppose
    0.96
     receive
    0.95
    Act Density 0.213%

    No Known Activations