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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking or food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acebook
    -0.78
     Hound
    -0.74
    Domain
    -0.73
    ylum
    -0.72
    href
    -0.72
    Asset
    -0.70
     Telecom
    -0.67
     Myster
    -0.66
     Rogers
    -0.66
     keynote
    -0.65
    POSITIVE LOGITS
     blender
    0.98
     rehe
    0.97
     freezer
    0.93
     omit
    0.92
     batch
    0.92
     thicker
    0.92
     pH
    0.90
    bsp
    0.90
     unfocusedRange
    0.90
     thickness
    0.89
    Act Density 0.295%

    No Known Activations