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

    Neuronpedia

    INDEX
    Explanations

    phrases related to singular entities and cohesion in processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Reſ
    -0.85
     itſelf
    -0.85
     Monfieur
    -0.81
     ſtre
    -0.79
     ſche
    -0.76
     الحره
    -0.75
     Anſ
    -0.75
     greateſt
    -0.72
     Conſ
    -0.72
     raiſ
    -0.71
    POSITIVE LOGITS
     vice
    0.54
     gynhyrchwyd
    0.53
    ENDIF
    0.47
    WriteBarrier
    0.47
    żu
    0.46
    publicain
    0.44
    inheit
    0.44
    BEAR
    0.43
    }>
    0.43
    }(),
    0.43
    Act Density 0.024%

    No Known Activations