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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective actions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourcem
    -0.17
    aurus
    -0.15
    viders
    -0.15
    lector
    -0.14
    rylic
    -0.14
    ÙĤات
    -0.14
    _DEPTH
    -0.14
     ÑĢазом
    -0.14
    adic
    -0.14
     Levin
    -0.14
    POSITIVE LOGITS
    ubre
    0.15
    623
    0.15
    awei
    0.15
     Kramer
    0.14
    indi
    0.14
    956
    0.14
    _pan
    0.14
    ILER
    0.13
     humans
    0.13
    kker
    0.13
    Act Density 0.095%

    No Known Activations