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

    Neuronpedia

    INDEX
    Explanations

    phrases related to essential components or foundational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itious
    -0.20
    ries
    -0.18
    arian
    -0.17
    rik
    -0.17
    riba
    -0.17
    orf
    -0.16
    ether
    -0.16
    rix
    -0.16
    ego
    -0.15
    ints
    -0.15
    POSITIVE LOGITS
    ference
    0.27
    quisites
    0.25
    quisite
    0.23
    clr
    0.21
    /Core
    0.21
    lates
    0.20
    /core
    0.20
    lla
    0.20
    .Core
    0.20
    ll
    0.20
    Act Density 0.017%

    No Known Activations