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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to definitions and their explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eros
    -0.19
    à¹ĥà¸Ī
    -0.17
    asse
    -0.16
    age
    -0.16
    ors
    -0.16
    ice
    -0.16
    ylon
    -0.16
    or
    -0.15
    ingly
    -0.15
    (TM
    -0.15
    POSITIVE LOGITS
    undef
    0.19
    nock
    0.17
     undef
    0.16
    /Instruction
    0.16
    hin
    0.15
    icie
    0.15
    idebar
    0.15
    endant
    0.15
    resher
    0.15
    _scope
    0.14
    Act Density 0.044%

    No Known Activations