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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amusement
    -0.79
     characteristic
    -0.75
     impossibility
    -0.71
     absence
    -0.68
     Tsukuyomi
    -0.66
     indifference
    -0.65
     speedy
    -0.65
     interest
    -0.65
     mischief
    -0.64
     memorable
    -0.64
    POSITIVE LOGITS
    activate
    1.32
    wrote
    1.16
    handedly
    1.14
    heartedly
    1.14
    register
    1.08
    task
    0.99
    pose
    0.96
    apply
    0.94
    installed
    0.94
    correct
    0.94
    Act Density 0.236%

    No Known Activations