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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baum
    -0.15
    ache
    -0.15
     deg
    -0.14
    ime
    -0.14
    igit
    -0.14
     stan
    -0.14
    orne
    -0.14
     Editors
    -0.14
    zw
    -0.14
     Stan
    -0.14
    POSITIVE LOGITS
     any
    0.21
    ä»»ä½ķ
    0.21
     ANY
    0.21
    à¹ĥà¸Ķ
    0.20
     qualquer
    0.20
    ANY
    0.19
     konkrét
    0.17
    JI
    0.16
    .sky
    0.15
     cualquier
    0.15
    Act Density 0.044%

    No Known Activations