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

    Neuronpedia

    INDEX
    Explanations

    terminology related to life changes and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĻĶ
    -0.19
    eldon
    -0.18
    ottes
    -0.17
    éļĨ
    -0.15
    uth
    -0.15
    £½
    -0.15
    otel
    -0.14
    оÑĢе
    -0.14
    905
    -0.14
    ême
    -0.14
    POSITIVE LOGITS
    atory
    0.17
    ILA
    0.17
     agent
    0.17
    agent
    0.16
    leta
    0.16
    echn
    0.15
     Agent
    0.15
    gent
    0.15
    Agent
    0.15
    /support
    0.14
    Act Density 0.219%

    No Known Activations