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

    Neuronpedia

    INDEX
    Explanations

    uses the word "shrink" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shrink" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coat
    -0.81
    iac
    -0.81
    abase
    -0.73
    oid
    -0.71
    bear
    -0.70
    gd
    -0.67
    trust
    -0.67
    Honest
    -0.66
    bah
    -0.66
    ibur
    -0.66
    POSITIVE LOGITS
     shr
    2.70
    shr
    0.88
     meg
    0.80
     tom
    0.79
    ħĭ
    0.76
     bark
    0.74
     multipl
    0.73
     swall
    0.72
     halves
    0.70
    ãĤ©
    0.69
    Act Density 0.001%

    No Known Activations