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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advice or caution

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing obligations or actions that need to be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lip
    -0.71
     Lambert
    -0.69
     spawned
    -0.67
    closed
    -0.66
     CAD
    -0.66
     Rust
    -0.66
     Baird
    -0.65
    linked
    -0.65
    vironment
    -0.61
    listed
    -0.60
    POSITIVE LOGITS
     rely
    1.07
     wait
    0.99
     learn
    0.97
     remind
    0.95
     abide
    0.93
     prioritize
    0.91
     keep
    0.90
     toe
    0.90
     give
    0.89
     obey
    0.89
    Act Density 0.102%

    No Known Activations