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

    Neuronpedia

    INDEX
    Explanations

    phrases related to special or notable things or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to entities or characteristics often associated with specific types of beings or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.86
    AMS
    -0.83
    pin
    -0.74
    head
    -0.73
    mith
    -0.73
    udeb
    -0.72
    WT
    -0.71
    ardless
    -0.70
    MAR
    -0.70
    zona
    -0.70
    POSITIVE LOGITS
    ial
    1.11
    ially
    0.98
    ient
    0.96
    eer
    0.91
    eers
    0.77
    eering
    0.75
    ré
    0.74
    ality
    0.74
    leness
    0.73
    ious
    0.73
    Act Density 0.031%

    No Known Activations