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

    Neuronpedia

    INDEX
    Explanations

    phrases related to issues or problems encountered in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hn
    -0.16
     SPDX
    -0.15
    .CustomButton
    -0.14
    ales
    -0.14
    esen
    -0.14
     RoundedRectangle
    -0.13
     Gest
    -0.13
    isk
    -0.13
    estre
    -0.13
    -sidebar
    -0.13
    POSITIVE LOGITS
    engo
    0.20
     scenario
    0.16
     am
    0.15
    acas
    0.15
    ëł
    0.14
    smouth
    0.14
     Scenario
    0.14
    antal
    0.14
    oola
    0.14
    uh
    0.14
    Act Density 0.051%

    No Known Activations