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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to interest and desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interest, interesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.63
     CURIAM
    -0.49
     Cloud
    -0.48
    Ӕ
    -0.48
     Mahl
    -0.48
    rrggbb
    -0.48
     Tsch
    -0.48
    VersionUID
    -0.46
     intptr
    -0.46
     Administrativna
    -0.45
    POSITIVE LOGITS
     Interest
    1.50
    Interest
    1.49
     interest
    1.47
    interest
    1.45
     INTEREST
    1.30
    INTEREST
    1.27
     interés
    1.26
     interes
    1.25
     Interests
    1.25
    Interes
    1.22
    Act Density 0.022%

    No Known Activations