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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases indicating hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pNet
    -0.17
    )((((
    -0.16
    ableObject
    -0.16
    omens
    -0.15
    eming
    -0.15
    ÙĨÛĮÙĨ
    -0.15
    .mx
    -0.14
    лиÑĪком
    -0.14
    %%%%%%%%%%%%%%%%
    -0.14
    DetailsService
    -0.14
    POSITIVE LOGITS
     someday
    0.16
    æıĽ
    0.15
     hook
    0.15
    rons
    0.15
    exact
    0.15
     dest
    0.15
    ạt
    0.14
    ijn
    0.14
    ieder
    0.14
    izz
    0.14
    Act Density 0.118%

    No Known Activations