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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or people's names with the common string "ith"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the substring "ith"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.77
     rodents
    -0.68
     lucky
    -0.67
    detail
    -0.67
     srf
    -0.65
    berman
    -0.64
    tails
    -0.63
    expression
    -0.62
     depress
    -0.61
     pione
    -0.61
    POSITIVE LOGITS
    otle
    1.08
    ith
    0.99
    iop
    0.95
    yll
    0.94
    ieth
    0.90
    ium
    0.88
    ythm
    0.82
    iasis
    0.82
    rones
    0.79
    reading
    0.77
    Act Density 0.010%

    No Known Activations