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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting essential items or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential recommendations or must-have items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etics
    -0.81
    ynthesis
    -0.75
    owered
    -0.69
    ripp
    -0.68
    ounded
    -0.68
    Roy
    -0.64
    ammad
    -0.64
    utics
    -0.63
    ames
    -0.63
     Courts
    -0.62
    POSITIVE LOGITS
     recommendation
    1.00
     item
    0.91
     destination
    0.86
     contender
    0.82
     gadget
    0.80
     recommendations
    0.79
     performer
    0.79
     Helpful
    0.78
     refres
    0.77
     ingredient
    0.76
    Act Density 0.162%

    No Known Activations