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

    Neuronpedia

    INDEX
    Explanations

    words related to things being uncomplicated or straightforward

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe simplicity or ease of an action or task

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eters
    -0.90
    mbuds
    -0.83
    hips
    -0.78
    reon
    -0.74
    raints
    -0.73
    geist
    -0.70
    akin
    -0.70
    arians
    -0.69
     Opera
    -0.68
    grave
    -0.68
    POSITIVE LOGITS
     prey
    0.84
    Jet
    0.81
    going
    0.80
     easy
    0.76
    ãĥīãĥ©
    0.76
     bruising
    0.75
    wallet
    0.74
    wired
    0.73
     forgiving
    0.71
     enough
    0.70
    Act Density 0.025%

    No Known Activations