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

    Neuronpedia

    INDEX
    Explanations

    situations related to hiding or seeking safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icina
    -0.17
    nova
    -0.15
     traged
    -0.15
    icana
    -0.14
    PK
    -0.14
    INET
    -0.14
    Priority
    -0.14
    iaux
    -0.14
    ais
    -0.14
    аниÑĨ
    -0.14
    POSITIVE LOGITS
    ero
    0.16
     conceal
    0.15
    -await
    0.15
     hiding
    0.15
    ël
    0.14
     Away
    0.14
     booth
    0.14
     hides
    0.14
    ering
    0.14
     cover
    0.14
    Act Density 0.114%

    No Known Activations