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

    Neuronpedia

    INDEX
    Explanations

    references to communal responsibilities and individual actions that impact the community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    маз
    -0.14
    elight
    -0.14
    ĶåĽŀ
    -0.14
    asil
    -0.13
    idget
    -0.13
     Compass
    -0.13
    efon
    -0.13
    ething
    -0.13
    ause
    -0.13
    hill
    -0.13
    POSITIVE LOGITS
    gnore
    0.14
    imos
    0.14
    modo
    0.14
     semiclass
    0.14
    éľ²
    0.14
     &
    0.13
    sis
    0.13
    mps
    0.13
    ournal
    0.13
    306
    0.13
    Act Density 0.074%

    No Known Activations