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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performing tasks and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to analytical tasks and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urated
    -0.72
    è¦
    -0.66
    oor
    -0.65
    stood
    -0.64
    angered
    -0.63
    heid
    -0.63
    raltar
    -0.62
    天
    -0.61
    éŃĶ
    -0.61
     porous
    -0.59
    POSITIVE LOGITS
    tests
    0.93
     homework
    0.83
     ourselves
    0.79
     yourselves
    0.78
     differently
    0.78
     myself
    0.78
     yourself
    0.76
     calculations
    0.76
     simulations
    0.76
     rounds
    0.75
    Act Density 0.180%

    No Known Activations