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

    Neuronpedia

    INDEX
    Explanations

    words related to argumentation and persuasion

    oai_token-act-pair · gpt-3.5-turbo

    the word "el" and its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.84
     Debor
    -0.73
    æĸ¹
    -0.69
    itives
    -0.59
    SourceFile
    -0.58
    CV
    -0.58
     Seym
    -0.58
     DPR
    -0.57
    Know
    -0.57
     Know
    -0.57
    POSITIVE LOGITS
    oaded
    1.06
    ength
    1.06
    ibrary
    1.05
    izabeth
    1.04
    estial
    1.02
    oad
    1.00
    baum
    1.00
    phia
    0.99
    ounge
    0.94
    abor
    0.93
    Act Density 0.049%

    No Known Activations