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

    Neuronpedia

    INDEX
    Explanations

    terms related to self-expression and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quet
    -0.17
    ungan
    -0.15
    mares
    -0.15
    ok
    -0.15
    uta
    -0.14
    roma
    -0.14
    ahren
    -0.14
    egas
    -0.14
    ichi
    -0.14
    onga
    -0.14
    POSITIVE LOGITS
    aldi
    0.16
    ormsg
    0.15
    Bubble
    0.15
    _Syntax
    0.15
    nest
    0.15
    abelle
    0.14
    dG
    0.14
    ample
    0.14
    mond
    0.14
    amine
    0.14
    Act Density 0.060%

    No Known Activations