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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and terms related to rules or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesi
    -0.17
    és
    -0.15
    аÑĢамеÑĤ
    -0.15
    .gwt
    -0.15
    lev
    -0.15
    ÙĨÛĮÙĨ
    -0.15
    inct
    -0.15
    念
    -0.14
    _term
    -0.14
    ignon
    -0.14
    POSITIVE LOGITS
     Conditions
    0.21
    conditions
    0.19
    Conditions
    0.19
     conditions
    0.19
     CONDITIONS
    0.19
    Condition
    0.19
     condition
    0.19
    condition
    0.18
     Condition
    0.17
    _conditions
    0.17
    Act Density 0.007%

    No Known Activations