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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate attraction or appeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .firebaseapp
    -0.16
    arbon
    -0.15
    vida
    -0.15
    ovah
    -0.14
     misc
    -0.14
    arez
    -0.14
    ardon
    -0.14
    .Override
    -0.14
    FillColor
    -0.14
    ills
    -0.14
    POSITIVE LOGITS
     drawn
    0.27
     irresist
    0.26
     attraction
    0.24
     away
    0.21
     attracted
    0.21
     magnet
    0.20
     Ø¥ÙĦÙĬÙĩ
    0.20
     towards
    0.19
     into
    0.18
    Attr
    0.18
    Act Density 0.040%

    No Known Activations