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

    Neuronpedia

    INDEX
    Explanations

    references to personal ownership or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mi
    -0.20
     themselves
    -0.18
    incy
    -0.16
    mand
    -0.15
    no
    -0.15
    long
    -0.15
    mu
    -0.15
    rance
    -0.14
    mat
    -0.14
    me
    -0.14
    POSITIVE LOGITS
    embros
    0.27
    opia
    0.26
    opic
    0.25
    rtle
    0.23
    anmar
    0.23
    riad
    0.21
    adows
    0.21
    batis
    0.20
    /us
    0.19
    zzo
    0.19
    Act Density 0.197%

    No Known Activations