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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consequences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redients
    -0.63
    elser
    -0.52
     usati
    -0.52
     sehari
    -0.51
     gewüns
    -0.51
    avorite
    -0.51
    anke
    -0.49
     parted
    -0.49
     Fian
    -0.49
     gespe
    -0.49
    POSITIVE LOGITS
     obstante
    0.92
     resourceCulture
    0.77
    theless
    0.77
    μφωνα
    0.75
     unknownFields
    0.74
    parsedMessage
    0.70
    ագրություններ
    0.70
    DrawerToggle
    0.70
    piram
    0.67
    epam
    0.65
    Act Density 0.107%

    No Known Activations