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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being capable of doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Registered
    -0.76
    cloth
    -0.76
    isite
    -0.72
    bilt
    -0.70
    scene
    -0.66
    gun
    -0.66
    era
    -0.65
    backer
    -0.64
     Shots
    -0.63
     Tradition
    -0.63
    POSITIVE LOGITS
     delivering
    1.09
     sustaining
    1.06
     handling
    1.06
     withstand
    1.04
     inflicting
    1.03
     achieving
    1.02
     detecting
    1.02
     producing
    1.00
     extracting
    1.00
     generating
    0.99
    Act Density 0.070%

    No Known Activations