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

    Neuronpedia

    INDEX
    Explanations

    the presence of citations or references within scientific or academic text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    τουργ
    -0.66
    APAN
    -0.62
    theless
    -0.59
    tyard
    -0.58
    theim
    -0.58
    tedly
    -0.58
     together
    -0.57
    ínsula
    -0.56
    возможно
    -0.56
    ATUM
    -0.55
    POSITIVE LOGITS
    tanleria
    0.75
     svolta
    0.67
     ***!
    0.65
     saites
    0.65
    calciatore
    0.60
    Composable
    0.59
    omitempty
    0.58
     fundada
    0.56
    canestro
    0.56
    ."-
    0.56
    Act Density 0.252%

    No Known Activations