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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to built-in features or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asso
    -0.16
    ιβ
    -0.15
    enko
    -0.15
    .sponge
    -0.14
    indr
    -0.14
    lor
    -0.14
    Assignable
    -0.14
    SenderId
    -0.14
    hem
    -0.14
    aptcha
    -0.14
    POSITIVE LOGITS
    θÏħ
    0.17
    ocha
    0.16
    /embed
    0.15
     McD
    0.15
    IRTH
    0.14
    üst
    0.14
    ForObject
    0.13
    Äħd
    0.13
    utzer
    0.13
    adu
    0.13
    Act Density 0.010%

    No Known Activations