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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user interface instructions

    oai_token-act-pair · gpt-3.5-turbo

    directives or instructions related to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.70
    raped
    -0.68
    blogspot
    -0.64
    riots
    -0.62
    quarters
    -0.62
    furt
    -0.62
    living
    -0.61
    cedented
    -0.60
    mere
    -0.59
    announced
    -0.58
    POSITIVE LOGITS
    ggles
    1.52
     activate
    1.24
     toggle
    1.14
     retrieve
    1.13
     initiate
    1.10
     indicate
    1.10
     obtain
    1.09
     locate
    1.09
     signify
    1.06
     navigate
    1.05
    Act Density 0.084%

    No Known Activations