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

    Neuronpedia

    INDEX
    Explanations

    positive adverbs that describe the satisfactory state of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions that convey appreciation for things being well-organized or presented positively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gate
    -0.70
    orno
    -0.67
    iens
    -0.65
     journalism
    -0.64
     Killer
    -0.62
    olan
    -0.62
    eway
    -0.61
    eport
    -0.60
    iferation
    -0.60
     verbs
    -0.60
    POSITIVE LOGITS
    baum
    0.92
    mint
    0.82
    ãĤ©
    0.81
     suited
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.74
     situated
    0.71
     Gleaming
    0.69
    lishes
    0.68
     illustrates
    0.68
    istered
    0.68
    Act Density 0.022%

    No Known Activations