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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating travel or movement to different locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entit
    -0.75
    ÃŃs
    -0.75
    iron
    -0.71
    ouse
    -0.69
    osi
    -0.68
     Originally
    -0.68
    Introduced
    -0.67
    illin
    -0.66
    ois
    -0.66
    killer
    -0.65
    POSITIVE LOGITS
     consultations
    0.93
     dinner
    0.87
     lunch
    0.87
     repairs
    0.84
     meetings
    0.84
     interviews
    0.84
     reasons
    0.83
     breakfast
    0.82
     clarification
    0.81
     questioning
    0.81
    Act Density 0.132%

    No Known Activations