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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns, references to books, and relationships

    oai_token-act-pair · gemini-2.0-flash

    expressions of affection or appreciation

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

    Positive sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.72
    ParallelGroup
    -0.68
     Reverso
    -0.68
     useRouter
    -0.64
    writeField
    -0.59
     IndexPath
    -0.59
    JNIEnv
    -0.58
    IsContent
    -0.57
    SourceChecksum
    -0.56
    adpleegd
    -0.56
    POSITIVE LOGITS
     loved
    1.35
     liked
    1.20
     Loved
    1.16
     LOVED
    1.14
    loved
    1.10
    Loved
    1.06
     Liked
    0.97
     enjoyed
    0.95
    Enjoyed
    0.80
     adored
    0.78
    Act Density 2.532%

    No Known Activations