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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive qualities or achievements

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating creation or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.67
     toured
    -0.65
    inav
    -0.64
    Liter
    -0.63
    usterity
    -0.62
     handed
    -0.61
     socket
    -0.60
    \-
    -0.59
     sidx
    -0.59
    kr
    -0.59
    POSITIVE LOGITS
     ample
    0.81
     plenty
    0.74
     undeniable
    0.72
    bryce
    0.71
    quartered
    0.69
    requisite
    0.69
     tremend
    0.68
     observers
    0.68
     unmist
    0.68
     overshadow
    0.67
    Act Density 0.241%

    No Known Activations