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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future timeframes or delays in plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ừa
    -0.15
    \Doctrine
    -0.15
    lica
    -0.15
    .createClass
    -0.14
    ius
    -0.14
    /Area
    -0.14
    erts
    -0.14
    ubat
    -0.13
    erte
    -0.13
    éģº
    -0.13
    POSITIVE LOGITS
     away
    0.51
     Away
    0.44
    away
    0.38
    Away
    0.38
     distant
    0.31
    -away
    0.30
     horizon
    0.25
     weg
    0.24
     Horizon
    0.24
     off
    0.21
    Act Density 0.019%

    No Known Activations