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

    Neuronpedia

    INDEX
    Explanations

    elements related to coding syntax and testing assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .BLL
    -0.15
    opers
    -0.14
    \Module
    -0.14
    airs
    -0.13
     reg
    -0.13
     Fear
    -0.13
    uds
    -0.13
     Amen
    -0.13
     conflict
    -0.13
    ics
    -0.13
    POSITIVE LOGITS
    .assertThat
    0.26
     assertThat
    0.18
    RITE
    0.16
    Matcher
    0.16
    ï¸
    0.16
     Matchers
    0.16
    Iterable
    0.16
    Matchers
    0.15
    inz
    0.15
     Kaplan
    0.15
    Act Density 0.004%

    No Known Activations