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

    Neuronpedia

    INDEX
    Explanations

    expressions related to aspirations and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.15
     invariant
    -0.14
    atra
    -0.14
    apa
    -0.14
    UF
    -0.14
    osu
    -0.14
    avan
    -0.14
    atis
    -0.14
     Settlement
    -0.14
    elle
    -0.14
    POSITIVE LOGITS
    åıªæĺ¯
    0.19
     limited
    0.18
    ingleton
    0.18
     confines
    0.17
     only
    0.16
     confined
    0.16
    ève
    0.16
    ableView
    0.16
     Limited
    0.16
    $MESS
    0.15
    Act Density 0.189%

    No Known Activations