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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ent"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    side
    -0.68
    Ø©
    -0.65
    CTV
    -0.65
    STON
    -0.64
    head
    -0.64
    ackets
    -0.62
    Äĩ
    -0.62
    ç¥ŀ
    -0.60
    issance
    -0.60
    ulner
    -0.59
    POSITIVE LOGITS
    ropy
    1.31
    ucky
    1.21
    ertain
    1.13
    ral
    1.08
    hus
    1.02
    rification
    1.01
    reprene
    1.00
    rance
    0.99
    acles
    0.99
    orian
    0.96
    Act Density 0.037%

    No Known Activations