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

    Neuronpedia

    INDEX
    Explanations

    conditions or factors that influence outcomes or variables in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.20
    dea
    -0.18
    eres
    -0.17
    ionale
    -0.16
    erne
    -0.15
    eras
    -0.15
    izontally
    -0.15
    ardu
    -0.15
    ÏĨαÏģ
    -0.15
    boa
    -0.14
    POSITIVE LOGITS
     upon
    0.33
    upon
    0.26
     Upon
    0.26
    Upon
    0.26
    ant
    0.25
    ents
    0.23
     sensit
    0.22
     crucial
    0.21
    ends
    0.20
    ently
    0.20
    Act Density 0.023%

    No Known Activations