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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positions or locations, such as "top of the line" or "out of shape."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" and its contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     earthqu
    -0.59
     conflic
    -0.51
    ģ«
    -0.50
     proport
    -0.48
     eleph
    -0.48
     muster
    -0.47
     departing
    -0.46
     Aires
    -0.46
     tremend
    -0.44
     reluct
    -0.44
    POSITIVE LOGITS
    -
    1.43
    -[
    1.18
    -$
    1.13
    -)
    1.11
    -(
    1.09
    %-
    1.03
    âĢij
    1.03
    -'
    1.02
    -.
    1.01
    '-
    1.01
    Act Density 0.181%

    No Known Activations