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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs and their variations indicating intentions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.83
     millenn
    -0.69
    anooga
    -0.68
    tun
    -0.65
     fortun
    -0.64
    oret
    -0.64
    good
    -0.61
     adolesc
    -0.60
     Canary
    -0.60
    lon
    -0.59
    POSITIVE LOGITS
     lose
    1.19
     rethink
    1.14
     stumble
    1.13
     abandon
    1.10
     become
    1.08
     seek
    1.05
     hesitate
    1.05
     flee
    1.05
     pursue
    1.04
     emit
    1.03
    Act Density 0.049%

    No Known Activations