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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive feelings or sentiments related to events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĩе
    -0.15
    nob
    -0.14
    ason
    -0.14
    ned
    -0.14
    planes
    -0.14
    ê°Ħ
    -0.14
    èo
    -0.13
     pán
    -0.13
    PY
    -0.13
    adlo
    -0.13
    POSITIVE LOGITS
     bid
    0.17
    .netbeans
    0.15
    stellen
    0.14
    ground
    0.14
    _gradients
    0.14
     Neck
    0.13
    Bid
    0.13
    akah
    0.13
    -ground
    0.13
    wave
    0.13
    Act Density 0.041%

    No Known Activations