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

    Neuronpedia

    INDEX
    Explanations

    words related to scheduled events or activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to achieving or reaching something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.97
    govtrack
    -0.91
    iquid
    -0.87
    vernment
    -0.78
    é¾įå
    -0.77
     Barclays
    -0.73
     contrace
    -0.73
    inals
    -0.71
    notation
    -0.71
    merce
    -0.69
    POSITIVE LOGITS
    uled
    0.96
    apeake
    0.84
    bones
    0.82
    bone
    0.82
    ambers
    0.82
    imer
    0.79
    dar
    0.76
    nee
    0.73
    lish
    0.73
    nut
    0.72
    Act Density 0.025%

    No Known Activations