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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and adjectives, especially in the possessive form

    oai_token-act-pair · gemini-2.0-flash

    words related to personal experiences and memories

    np_token-act-pair-logits · gpt-4o-mini

    experiences/feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.90
    TagMode
    -0.87
    AccessorTable
    -0.80
    elemField
    -0.78
    InjectAttribute
    -0.75
     AssemblyCulture
    -0.74
    AndEndTag
    -0.71
    PerformLayout
    -0.70
    脚注の使い方
    -0.65
    цездатний
    -0.64
    POSITIVE LOGITS
    
    0.61
     experiences
    0.61
     frustrations
    0.57
     escap
    0.55
     preferences
    0.54
     sür
    0.53
     desires
    0.53
     adventures
    0.52
    habit
    0.51
     habit
    0.50
    Act Density 1.927%

    No Known Activations