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

    Neuronpedia

    INDEX
    Explanations

    phrases welcoming someone to a specific place

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intent or goal-oriented actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.74
    NPR
    -0.72
    ews
    -0.70
    SPONSORED
    -0.70
    cod
    -0.66
    alys
    -0.65
     Benn
    -0.65
    PU
    -0.64
    corn
    -0.64
    éĽ
    -0.63
    POSITIVE LOGITS
    yles
    0.71
    ebin
    0.71
     Aires
    0.69
    phies
    0.67
     shaft
    0.66
     Beyond
    0.65
     Savior
    0.64
    enhagen
    0.64
     Ple
    0.64
     Pebble
    0.61
    Act Density 0.000%

    No Known Activations