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

    Neuronpedia

    INDEX
    Explanations

    expressions of sentiment and personal reflection related to positive experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perus
    -0.48
     perla
    -0.46
     naturelles
    -0.46
     spray
    -0.44
    gany
    -0.44
     Jahrgang
    -0.43
    ess
    -0.42
     falt
    -0.40
     vertes
    -0.40
     poliuret
    -0.40
    POSITIVE LOGITS
    nasium
    0.77
     enjoyable
    0.76
    AddTagHelper
    0.71
     createSprite
    0.69
     rewarding
    0.67
     pleasurable
    0.66
     orgas
    0.64
     rewards
    0.64
     thrills
    0.64
     exhilarating
    0.63
    Act Density 0.236%

    No Known Activations