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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "right" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    省市镇
    -0.83
    lgica
    -0.82
     BCC
    -0.75
     invokingState
    -0.74
    })();
    -0.73
     RCP
    -0.72
    Diweddarwch
    -0.72
    amerikanischer
    -0.71
    MigrationBuilder
    -0.71
     CGA
    -0.70
    POSITIVE LOGITS
     down
    0.71
     close
    0.68
     right
    0.68
     out
    0.66
     away
    0.65
     allá
    0.65
    jusqu
    0.63
     around
    0.62
    setcounter
    0.62
     back
    0.61
    Act Density 0.204%

    No Known Activations