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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing emotional experiences and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    at the sky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.69
    transQ
    -0.68
    soever
    -0.60
    __(/*!
    -0.59
    AddTagHelper
    -0.59
    astéroïdes
    -0.58
    loem
    -0.57
    IUrlHelper
    -0.57
    <pad>
    -0.56
    <unused28>
    -0.56
    POSITIVE LOGITS
     menatap
    0.40
     looking
    0.38
     looks
    0.34
     quedado
    0.32
     defaultstate
    0.31
     qualités
    0.30
     nhìn
    0.29
     capacidades
    0.29
     Sternen
    0.29
     rendu
    0.29
    Act Density 0.017%

    No Known Activations