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

    Neuronpedia

    INDEX
    Explanations

    verbs that imply prediction or future action

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating future actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    washer
    -0.73
    Quantity
    -0.72
    ONSORED
    -0.70
     competitor
    -0.67
     candidacy
    -0.66
     predecessor
    -0.65
     counterpart
    -0.62
    ixties
    -0.62
     successor
    -0.61
     wounding
    -0.60
    POSITIVE LOGITS
     alike
    1.01
    ateurs
    0.99
     beware
    0.94
     routinely
    0.89
     rejoice
    0.86
    vae
    0.86
     warned
    0.80
     consulted
    0.79
     speculate
    0.77
     agree
    0.76
    Act Density 0.499%

    No Known Activations