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

    Neuronpedia

    INDEX
    Explanations

    phrases related to newsletters or articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ERS" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bed
    -0.66
    spe
    -0.66
     reinforcement
    -0.65
    ãĥĥ
    -0.65
    ãĥĥãĤ¯
    -0.65
     Chak
    -0.63
    steel
    -0.60
     Persian
    -0.60
     Sop
    -0.59
     san
    -0.59
    POSITIVE LOGITS
    VILLE
    1.09
    poons
    1.07
    hip
    1.06
    IAL
    1.05
    FIELD
    1.05
    BUR
    1.04
    ELF
    1.03
    HAM
    0.99
    hips
    0.97
    cream
    0.96
    Act Density 0.008%

    No Known Activations