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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to preferences and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angelo
    -0.18
    quee
    -0.16
    romo
    -0.16
    urgy
    -0.15
    inea
    -0.15
    spiel
    -0.15
    790
    -0.15
    elsing
    -0.14
    rapy
    -0.14
    suming
    -0.14
    POSITIVE LOGITS
    entially
    0.39
    ential
    0.36
    ably
    0.22
    encing
    0.18
    renc
    0.18
     prefer
    0.17
    lag
    0.17
    ensi
    0.17
    idian
    0.17
    enced
    0.16
    Act Density 0.027%

    No Known Activations