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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to the entirety or entirety of a situation or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to "the whole thing" as a concept or theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.62
    ello
    -0.62
     occasional
    -0.60
     Samar
    -0.59
     prevailing
    -0.57
    Soul
    -0.57
     heels
    -0.56
     brakes
    -0.56
     affinity
    -0.55
     reflective
    -0.55
    POSITIVE LOGITS
    代
    0.88
    ãĤ¼ãĤ¦ãĤ¹
    0.87
     except
    0.81
    yss
    0.78
     laun
    0.76
    Tes
    0.72
    äºĶ
    0.70
    çIJ
    0.69
    except
    0.69
     Jinping
    0.68
    Act Density 0.115%

    No Known Activations