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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "interest" related to various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Napa
    -0.69
    scriptcase
    -0.68
     Cabrera
    -0.68
    akana
    -0.67
    izop
    -0.65
    DNEY
    -0.65
    — 
    -0.64
     Dion
    -0.63
    لمانيا
    -0.62
     nélk
    -0.61
    POSITIVE LOGITS
     interest
    2.02
     Interest
    2.00
     interests
    1.96
    Interest
    1.88
     INTEREST
    1.88
    interest
    1.84
     Interests
    1.80
    INTEREST
    1.71
    interests
    1.60
    Interests
    1.60
    Act Density 0.056%

    No Known Activations