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

    Neuronpedia

    INDEX
    Explanations

    emotional responses related to positive and negative feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viewDidLoad
    -0.54
    kauft
    -0.50
    Rights
    -0.48
     gloire
    -0.48
     Rights
    -0.48
    beled
    -0.47
    hiv
    -0.47
    Przypisy
    -0.47
    yship
    -0.47
    υσ
    -0.46
    POSITIVE LOGITS
    InvalidProtocol
    0.64
    scriptcase
    0.64
     inspiration
    0.63
     inspirational
    0.63
     uplifting
    0.59
     defaultstate
    0.58
     inspiring
    0.56
     Italijanski
    0.56
     soothing
    0.56
     depressing
    0.54
    Act Density 0.120%

    No Known Activations