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

    Neuronpedia

    INDEX
    Explanations

    phrases related to using something for a specific purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "use" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.58
     apologizing
    -0.56
     apologies
    -0.54
     citation
    -0.53
     fumble
    -0.52
     ado
    -0.52
     Mile
    -0.52
     typo
    -0.51
    iatus
    -0.50
     forgetting
    -0.50
    POSITIVE LOGITS
     alongside
    0.98
     efficiently
    0.82
    uate
    0.75
    dress
    0.74
    estyles
    0.70
    fill
    0.69
     therein
    0.68
    OHN
    0.67
    itely
    0.67
    agine
    0.67
    Act Density 0.349%

    No Known Activations