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

    Neuronpedia

    INDEX
    Explanations

    text related to mechanical objects and machinery

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to physical objects or living beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dstg
    -0.61
     respons
    -0.59
    ENN
    -0.59
    Travel
    -0.58
    awar
    -0.57
    ALT
    -0.56
     grain
    -0.55
    Balt
    -0.55
    och
    -0.55
     light
    -0.55
    POSITIVE LOGITS
    theless
    1.19
    tenance
    0.95
    terday
    0.81
    DragonMagazine
    0.80
     wip
    0.76
    /-
    0.72
    ratulations
    0.71
    ionage
    0.71
    obbies
    0.70
    vous
    0.68
    Act Density 0.175%

    No Known Activations