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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dialogue and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elemField
    -0.75
     ſtre
    -0.66
    rungsseite
    -0.63
     CWE
    -0.63
     uſ
    -0.62
    migrationBuilder
    -0.61
     ejus
    -0.61
     ſtate
    -0.60
     juſ
    -0.60
     ſub
    -0.60
    POSITIVE LOGITS
     shoved
    0.54
     shoving
    0.53
    ')[
    0.50
     cał
    0.49
     glancing
    0.47
     scow
    0.47
    läufer
    0.47
     хоть
    0.46
     thankfully
    0.46
    albeit
    0.46
    Act Density 0.092%

    No Known Activations