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

    Neuronpedia

    INDEX
    Explanations

    phrases related to matters of policy and international relations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that suggest addition or connection between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meric
    -0.77
    kees
    -0.77
    ãĥĥãĤ¯
    -0.74
    ãĥ¯ãĥ³
    -0.71
    usha
    -0.68
    oeuv
    -0.66
     Eat
    -0.65
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.63
    ãĤ©
    -0.63
    ãģĨ
    -0.62
    POSITIVE LOGITS
     consequently
    1.02
     especially
    0.94
     elsewhere
    0.93
     hence
    0.93
     indeed
    0.90
     wider
    0.86
     certainly
    0.86
     particularly
    0.85
     consequ
    0.83
     possibly
    0.82
    Act Density 0.319%

    No Known Activations