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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or modify a clause, particularly relative pronouns and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.73
    AndEndTag
    -0.64
     disambiguazione
    -0.60
     ivelany
    -0.59
     ComVisible
    -0.56
    MessageOf
    -0.56
    LookAnd
    -0.53
    Tikang
    -0.50
     noDo
    -0.50
     StatelessWidget
    -0.49
    POSITIVE LOGITS
    .*")]
    0.45
     scope
    0.36
    =((
    0.34
     referrerpolicy
    0.34
     kapak
    0.34
     space
    0.32
    (((
    0.32
     room
    0.31
     (((
    0.30
    ValueType
    0.29
    Act Density 0.016%

    No Known Activations