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

    Neuronpedia

    INDEX
    Explanations

    dense and concentrated areas or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to density, particularly in urban or environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.84
    skill
    -0.81
    porary
    -0.74
    obil
    -0.70
    bara
    -0.69
    OPA
    -0.69
    OTO
    -0.68
    VR
    -0.66
    ership
    -0.66
    Army
    -0.65
    POSITIVE LOGITS
     tracts
    0.97
     dense
    0.92
     enough
    0.86
    packed
    0.83
     congest
    0.81
     densely
    0.75
    iband
    0.74
     fog
    0.74
     bundles
    0.74
     jung
    0.73
    Act Density 0.019%

    No Known Activations