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

    Neuronpedia

    INDEX
    Explanations

    prepositions 'at' followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "look at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.67
    nown
    -0.66
    trap
    -0.66
    stress
    -0.65
    widget
    -0.65
    cation
    -0.64
    soever
    -0.64
    Skill
    -0.64
    DON
    -0.63
    Cry
    -0.63
    POSITIVE LOGITS
    ĸļ
    0.75
    hetically
    0.70
    awed
    0.69
    ibly
    0.69
     them
    0.68
    adata
    0.67
     how
    0.67
    ibilities
    0.66
     least
    0.65
    rical
    0.64
    Act Density 0.068%

    No Known Activations