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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problems or challenges within a given context

    oai_token-act-pair · gpt-3.5-turbo

    statements about necessity or ongoing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */
    -0.74
    bilt
    -0.68
    avier
    -0.67
     caution
    -0.66
    retty
    -0.66
    loo
    -0.65
    lique
    -0.64
    #$
    -0.63
    lex
    -0.61
    RAY
    -0.61
    POSITIVE LOGITS
     plag
    0.90
     underpin
    0.81
     surround
    0.80
     hallmark
    0.76
    ģĸ
    0.68
     besie
    0.66
     emanating
    0.66
     accrued
    0.65
     engulf
    0.64
     litter
    0.63
    Act Density 0.246%

    No Known Activations