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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dependency and reliance on certain conditions or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caps
    -0.66
    interstitial
    -0.65
    76561
    -0.64
     rushes
    -0.63
    ãĥīãĥ©
    -0.62
     Mush
    -0.61
    bugs
    -0.58
    çĦ
    -0.57
    boro
    -0.55
     Reporting
    -0.55
    POSITIVE LOGITS
     greatly
    1.23
     critically
    1.18
     heavily
    1.18
     enormously
    1.10
     upon
    1.09
     hugely
    1.07
     largely
    1.07
     entirely
    1.06
     partly
    1.01
     principally
    0.98
    Act Density 0.025%

    No Known Activations