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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "just" is used in a context that denotes a small or limited quantity

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "just"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.71
     challeng
    -0.69
     seiz
    -0.68
     trave
    -0.68
     includ
    -0.67
    undai
    -0.67
    glomer
    -0.66
    hovah
    -0.63
     subsequ
    -0.63
     nep
    -0.63
    POSITIVE LOGITS
    ifiable
    1.31
    ifications
    1.24
    ices
    0.94
    IFIC
    0.91
    ifiers
    0.89
    ICES
    0.89
    ifi
    0.85
    IFIED
    0.84
    if
    0.84
    ifier
    0.84
    Act Density 0.081%

    No Known Activations