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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that contain reflections, conditions, or questions related to people's feelings and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.59
    rungsseite
    -0.57
    EndGlobalSection
    -0.57
    Revenir
    -0.55
    vdots
    -0.55
     Administrativna
    -0.54
    Viitteet
    -0.52
     magasiner
    -0.52
     通販
    -0.52
    ittarius
    -0.52
    POSITIVE LOGITS
    ۖ
    0.52
    WriteTagHelper
    0.51
    ۚ
    0.50
    績
    0.47
    mockMvc
    0.47
    хьтан
    0.46
     reine
    0.45
     urm
    0.45
    amse
    0.44
    verture
    0.43
    Act Density 0.877%

    No Known Activations