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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions and summative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ätt
    -0.16
    걸
    -0.15
     걸
    -0.15
    load
    -0.15
     поÑĩаÑĤкÑĥ
    -0.14
    778
    -0.14
    etics
    -0.14
    .uk
    -0.14
    thing
    -0.14
    assis
    -0.14
    POSITIVE LOGITS
     Reached
    0.20
     reached
    0.20
    aires
    0.19
    arity
    0.17
    naire
    0.17
    ogy
    0.17
     remarks
    0.17
    aries
    0.17
    swith
    0.16
    Reached
    0.16
    Act Density 0.025%

    No Known Activations