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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating connections or combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     even
    -0.16
    este
    -0.14
    InOut
    -0.14
     EVEN
    -0.14
    ince
    -0.14
    .glide
    -0.14
    stin
    -0.13
    ifty
    -0.13
    ply
    -0.13
    entic
    -0.13
    POSITIVE LOGITS
    /or
    0.30
    rew
    0.26
     zwar
    0.25
    erson
    0.24
    REW
    0.24
    rea
    0.22
    reas
    0.22
    vanced
    0.21
    ROID
    0.21
    rogen
    0.20
    Act Density 0.235%

    No Known Activations