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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military actions and geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that signal cohesion or connection in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.95
     Pigs
    -0.83
    ojure
    -0.72
    INST
    -0.72
     Loren
    -0.70
    Xbox
    -0.70
    CLA
    -0.69
    ULTS
    -0.69
    OPLE
    -0.68
    assium
    -0.68
    POSITIVE LOGITS
    rogen
    1.23
    rogens
    1.10
     possibly
    0.96
     inventive
    0.83
     potentially
    0.83
     economical
    0.83
     intimate
    0.82
     unch
    0.82
     innovative
    0.82
     imaginative
    0.81
    Act Density 0.188%

    No Known Activations