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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax related to class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oom
    -0.16
    eut
    -0.15
    _TAC
    -0.15
    Agents
    -0.14
     Agents
    -0.14
     neglig
    -0.14
    vetica
    -0.14
     agents
    -0.14
    jure
    -0.14
    åĨĨ
    -0.13
    POSITIVE LOGITS
    orse
    0.15
    çĨ
    0.14
    rende
    0.14
    inski
    0.14
     hmac
    0.14
    LEGRO
    0.14
    ewood
    0.14
     Roose
    0.13
     Campus
    0.13
    itness
    0.13
    Act Density 0.007%

    No Known Activations