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

    Neuronpedia

    INDEX
    Explanations

    words related to employment, energy sources, hierarchies, and governmental activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALT
    -0.71
    ËĪ
    -0.65
    aband
    -0.62
     iT
    -0.61
    iom
    -0.61
    vs
    -0.59
    kernel
    -0.58
    ãĥ´ãĤ¡
    -0.57
    lopp
    -0.57
    antha
    -0.56
    POSITIVE LOGITS
     alike
    1.53
     respectively
    1.34
     depending
    0.76
     interchange
    0.72
     sectors
    0.71
     wings
    0.67
     approaches
    0.67
    depending
    0.63
     industries
    0.60
     regimes
    0.57
    Act Density 0.570%

    No Known Activations