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

    Neuronpedia

    INDEX
    Explanations

    topics related to academic publications and their references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Claus
    -0.16
     Tas
    -0.15
    _descriptor
    -0.15
     suck
    -0.15
    mana
    -0.14
    enn
    -0.14
     tact
    -0.14
     Mot
    -0.13
     twin
    -0.13
     Daniels
    -0.13
    POSITIVE LOGITS
    oplevel
    0.18
    ëĮ
    0.16
    TouchUpInside
    0.15
    arge
    0.15
    unnable
    0.14
    Äįem
    0.14
    ALLY
    0.14
    yx
    0.14
    alis
    0.14
    veh
    0.14
    Act Density 0.112%

    No Known Activations