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

    Neuronpedia

    INDEX
    Explanations

    themes related to school safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üb
    -0.16
    æĭ¬
    -0.15
    bins
    -0.15
    baby
    -0.14
    pedia
    -0.14
     anomal
    -0.14
    ανδ
    -0.14
    incare
    -0.13
    ircon
    -0.13
     base
    -0.13
    POSITIVE LOGITS
    semblies
    0.17
    pom
    0.15
     crossorigin
    0.15
    ibi
    0.14
    TG
    0.14
    _bh
    0.14
     Safety
    0.14
    PostMapping
    0.14
     rais
    0.14
     assemblies
    0.14
    Act Density 0.117%

    No Known Activations