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

    Neuronpedia

    INDEX
    Explanations

    phrases where the word "something" is followed by a description or noun

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "something" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOS
    -0.83
    eret
    -0.76
    ortex
    -0.71
    orks
    -0.71
    ildo
    -0.70
    otonin
    -0.70
    tor
    -0.68
     Shutterstock
    -0.67
    eds
    -0.67
    de
    -0.67
    POSITIVE LOGITS
     else
    1.43
     resembling
    1.26
     akin
    1.24
    Else
    0.96
     analogous
    0.87
     intangible
    0.86
     reminiscent
    0.85
     tangible
    0.84
     uncanny
    0.84
     similar
    0.84
    Act Density 0.054%

    No Known Activations