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

    Neuronpedia

    INDEX
    Explanations

    words related to expressions of appreciation and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lication
    -0.21
    iation
    -0.20
    WARD
    -0.19
    ackets
    -0.19
    ughters
    -0.18
    lesc
    -0.18
    ortion
    -0.18
    ward
    -0.17
    icks
    -0.17
    ings
    -0.16
    POSITIVE LOGITS
    e
    0.19
    point
    0.17
    eer
    0.16
    ors
    0.16
    ports
    0.16
    otine
    0.15
    ALE
    0.15
    emma
    0.15
    tar
    0.15
    ply
    0.14
    Act Density 0.052%

    No Known Activations