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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or liking towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.68
    orghini
    -0.59
     Idem
    -0.57
    それとも
    -0.56
     palsy
    -0.55
    obacz
    -0.54
    Estate
    -0.54
     OMITTED
    -0.54
    quitous
    -0.54
    ItemBackground
    -0.54
    POSITIVE LOGITS
    migrationBuilder
    0.81
     suitable
    0.77
    suitable
    0.72
     appropriate
    0.70
    appropriate
    0.64
     shall
    0.64
    priate
    0.64
    shall
    0.60
    Autoritní
    0.59
    __':
    0.59
    Act Density 0.119%

    No Known Activations